docs: define implementation-ready distributed GGUF roadmap
This commit is contained in:
Dobromir Popov
@@ -0,0 +1,39 @@
|
||||
<!-- GENERATED FROM prd.json — DO NOT EDIT AS AN INDEPENDENT SOURCE. prd.json IS AUTHORITATIVE. -->
|
||||
# DGR-017: Reconcile and clean the superseded DGR backlog
|
||||
|
||||
- **Status / triage:** specification only; `ready-for-agent`; `passes: false`
|
||||
- **Execution mode:** `AFK`
|
||||
- **Milestone:** `M0`
|
||||
- **Dependencies:** None
|
||||
- **Blocks (derived):** `DGR-018`, `DGR-019`, `DGR-027`, `DGR-054`
|
||||
- **Labels:** `area:provenance`, `area:cleanup`, `type:audit`, `priority:p0`, `ready-for-agent`
|
||||
- **Evidence class:** `model-free`
|
||||
- **Hardware:** `none`
|
||||
- **Model:** `generic`
|
||||
- **Upstream:** `no`
|
||||
|
||||
## Objective / description
|
||||
|
||||
Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`, source issue `.scratch/distributed-gguf-runtime/issues/017-reconcile-and-clean-the-superseded-dgr-backlog.md`, and evidence READMEs for dependencies (none) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Audit implementation reality, void inherited completion credit, and clean misleading backlog/stub baggage while preserving attributable evidence and accepted research.
|
||||
|
||||
## Acceptance criteria
|
||||
|
||||
- [ ] Compare the branch, old DGR-001..016 issue/pass states, evidence, and actual runtime sources; classify each output as reusable, reference-only, blocked, obsolete, or absent.
|
||||
- [ ] Record an authoritative old-to-new disposition and provenance; explicitly give no completion credit to any new story and note absent implementation/evidence.
|
||||
- [ ] Remove or archive only artifacts the audit proves obsolete while preserving accepted ADRs, useful research, raw benchmark evidence, and attributable reusable work.
|
||||
- [ ] Protect ignored build workspaces, generated protobuf outputs, Ralph logs, and model artifacts from accidental commits, and document every retained legacy artifact.
|
||||
- [ ] Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff.
|
||||
|
||||
## Shared quality gates
|
||||
|
||||
- Targeted deterministic tests pass; Python changes also pass `python -m compileall packages tests`.
|
||||
- `git diff --check` passes.
|
||||
- Default tests are model-download-free, API-credit-free, and GPU-free.
|
||||
- Evidence README records exact changed files, commands/results, limitations, and dependency handoff; no fabricated evidence or inherited completion credit.
|
||||
- Native changes pass focused out-of-tree CMake build and CTest; patch changes verify clean apply/check/reverse against the exact llama.cpp pin.
|
||||
- Runs are opt-in and record exact artifact/split hashes, runtime/upstream pin, backend/driver, hardware, network, commands, and raw metrics. Model artifacts use configured mounted-drive storage and never `/home`.
|
||||
- Preserve existing Transformers behavior and backend-agnostic Tracker routing/load balancing/billing/relay semantics unless an explicit versioned contract says otherwise. One scoped story commit is expected during execution, but this specification-materialization change is not committed.
|
||||
|
||||
## Evidence handoff
|
||||
|
||||
Write and verify `.scratch/distributed-gguf-runtime/evidence/DGR-017/README.md`. Until every criterion and applicable gate has real evidence, this story remains `passes: false`. Legacy evidence is provenance only, not completion credit.
|
||||
@@ -0,0 +1,39 @@
|
||||
<!-- GENERATED FROM prd.json — DO NOT EDIT AS AN INDEPENDENT SOURCE. prd.json IS AUTHORITATIVE. -->
|
||||
# DGR-018: Define canonical Ralph and Gitea metadata schema
|
||||
|
||||
- **Status / triage:** specification only; `ready-for-agent`; `passes: false`
|
||||
- **Execution mode:** `AFK`
|
||||
- **Milestone:** `M0`
|
||||
- **Dependencies:** `DGR-017`
|
||||
- **Blocks (derived):** `DGR-021`, `DGR-025`
|
||||
- **Labels:** `area:planning`, `area:gitea`, `type:infrastructure`, `priority:p0`, `ready-for-agent`
|
||||
- **Evidence class:** `model-free`
|
||||
- **Hardware:** `none`
|
||||
- **Model:** `generic`
|
||||
- **Upstream:** `no`
|
||||
|
||||
## Objective / description
|
||||
|
||||
Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`, source issue `.scratch/distributed-gguf-runtime/issues/018-define-canonical-ralph-and-gitea-metadata-schema.md`, and evidence READMEs for dependencies (DGR-017) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Make `prd.json` the validated source from which Markdown and Gitea issues can later be generated losslessly.
|
||||
|
||||
## Acceptance criteria
|
||||
|
||||
- [ ] Define fields for stable ID/title, labels, milestone, type, `dependsOn`, derived `blocks`, triage, evidence class, and hardware/model/upstream flags.
|
||||
- [ ] Validate that all stories start `passes: false`, use known dependencies, and have unique stable IDs.
|
||||
- [ ] Reject cycles, missing dependencies, mismatched generated `blocks`, duplicate titles/IDs, and generated artifacts claiming authority over `prd.json`.
|
||||
- [ ] Add deterministic model-free tests for parse, validation, and generation round trips.
|
||||
- [ ] Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff.
|
||||
|
||||
## Shared quality gates
|
||||
|
||||
- Targeted deterministic tests pass; Python changes also pass `python -m compileall packages tests`.
|
||||
- `git diff --check` passes.
|
||||
- Default tests are model-download-free, API-credit-free, and GPU-free.
|
||||
- Evidence README records exact changed files, commands/results, limitations, and dependency handoff; no fabricated evidence or inherited completion credit.
|
||||
- Native changes pass focused out-of-tree CMake build and CTest; patch changes verify clean apply/check/reverse against the exact llama.cpp pin.
|
||||
- Runs are opt-in and record exact artifact/split hashes, runtime/upstream pin, backend/driver, hardware, network, commands, and raw metrics. Model artifacts use configured mounted-drive storage and never `/home`.
|
||||
- Preserve existing Transformers behavior and backend-agnostic Tracker routing/load balancing/billing/relay semantics unless an explicit versioned contract says otherwise. One scoped story commit is expected during execution, but this specification-materialization change is not committed.
|
||||
|
||||
## Evidence handoff
|
||||
|
||||
Write and verify `.scratch/distributed-gguf-runtime/evidence/DGR-018/README.md`. Until every criterion and applicable gate has real evidence, this story remains `passes: false`. Legacy evidence is provenance only, not completion credit.
|
||||
@@ -0,0 +1,40 @@
|
||||
<!-- GENERATED FROM prd.json — DO NOT EDIT AS AN INDEPENDENT SOURCE. prd.json IS AUTHORITATIVE. -->
|
||||
# DGR-019: Lock alpha and beta performance contracts
|
||||
|
||||
- **Status / triage:** specification only; `ready-for-human`; `passes: false`
|
||||
- **Execution mode:** `HITL`
|
||||
- **Milestone:** `M0`
|
||||
- **Dependencies:** `DGR-017`
|
||||
- **Blocks (derived):** `DGR-020`, `DGR-044`, `DGR-054`
|
||||
- **Labels:** `area:performance`, `type:contract`, `priority:p0`, `gate:hitl`, `ready-for-human`
|
||||
- **Evidence class:** `release`
|
||||
- **Hardware:** `required`
|
||||
- **Model:** `generic+deepseek-v4`
|
||||
- **Upstream:** `no`
|
||||
|
||||
## Objective / description
|
||||
|
||||
Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`, source issue `.scratch/distributed-gguf-runtime/issues/019-lock-alpha-and-beta-performance-contracts.md`, and evidence READMEs for dependencies (DGR-017) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Freeze useful speed, correctness, memory-fit, and stop/go thresholds before implementation results are visible.
|
||||
|
||||
## Acceptance criteria
|
||||
|
||||
- [ ] Define controlled safetensors, whole-model GGUF, dense distributed GGUF, and V4 Flash distributed lanes with fixed prompts, context/output lengths, sampling, concurrency, hardware, and metrics.
|
||||
- [ ] Alpha requires correctness plus a human-approved useful-speed threshold; beta adds concurrency, long-context, failure, and sustained-throughput thresholds.
|
||||
- [ ] Separate quantization/model-fit gains from runtime, transport, batching, and kernel gains.
|
||||
- [ ] Treat quants and 2–4/10+ stage counts only as named certification scenarios; no product logic may hardcode them.
|
||||
- [ ] Lock thresholds and stop conditions in versioned machine-readable data before benchmark result ingestion.
|
||||
- [ ] Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff.
|
||||
|
||||
## Shared quality gates
|
||||
|
||||
- Targeted deterministic tests pass; Python changes also pass `python -m compileall packages tests`.
|
||||
- `git diff --check` passes.
|
||||
- Default tests are model-download-free, API-credit-free, and GPU-free.
|
||||
- Evidence README records exact changed files, commands/results, limitations, and dependency handoff; no fabricated evidence or inherited completion credit.
|
||||
- Native changes pass focused out-of-tree CMake build and CTest; patch changes verify clean apply/check/reverse against the exact llama.cpp pin.
|
||||
- Runs are opt-in and record exact artifact/split hashes, runtime/upstream pin, backend/driver, hardware, network, commands, and raw metrics. Model artifacts use configured mounted-drive storage and never `/home`.
|
||||
- Preserve existing Transformers behavior and backend-agnostic Tracker routing/load balancing/billing/relay semantics unless an explicit versioned contract says otherwise. One scoped story commit is expected during execution, but this specification-materialization change is not committed.
|
||||
|
||||
## Evidence handoff
|
||||
|
||||
Write and verify `.scratch/distributed-gguf-runtime/evidence/DGR-019/README.md`. Until every criterion and applicable gate has real evidence, this story remains `passes: false`. Legacy evidence is provenance only, not completion credit.
|
||||
@@ -0,0 +1,39 @@
|
||||
<!-- GENERATED FROM prd.json — DO NOT EDIT AS AN INDEPENDENT SOURCE. prd.json IS AUTHORITATIVE. -->
|
||||
# DGR-020: Run the controlled whole-model GGUF baseline
|
||||
|
||||
- **Status / triage:** specification only; `ready-for-human`; `passes: false`
|
||||
- **Execution mode:** `HITL`
|
||||
- **Milestone:** `M0`
|
||||
- **Dependencies:** `DGR-019`
|
||||
- **Blocks (derived):** `DGR-054`
|
||||
- **Labels:** `area:performance`, `type:benchmark`, `priority:p0`, `gate:hitl`, `ready-for-human`
|
||||
- **Evidence class:** `real-hardware`
|
||||
- **Hardware:** `required`
|
||||
- **Model:** `generic`
|
||||
- **Upstream:** `no`
|
||||
|
||||
## Objective / description
|
||||
|
||||
Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`, source issue `.scratch/distributed-gguf-runtime/issues/020-run-the-controlled-whole-model-gguf-baseline.md`, and evidence READMEs for dependencies (DGR-019) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Execute the locked safetensors and whole-model llama.cpp lanes before distributed implementation results can influence the decision.
|
||||
|
||||
## Acceptance criteria
|
||||
|
||||
- [ ] Run the exact DGR-019 safetensors and whole-model llama.cpp benchmark lanes with locked prompts, lengths, sampling, concurrency, hardware, and artifact/runtime identities.
|
||||
- [ ] Record raw machine-readable correctness, TTFT, prefill/decode, throughput, latency, memory, artifact-size, failure, and quality-drift metrics without ingesting distributed implementation results.
|
||||
- [ ] Separate quantization/model-fit effects from runtime/kernel effects and preserve failed or unavailable lanes honestly.
|
||||
- [ ] Publish a threshold-based `go`, `optimize baseline`, or `stop` decision without changing the locked contract.
|
||||
- [ ] Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff.
|
||||
|
||||
## Shared quality gates
|
||||
|
||||
- Targeted deterministic tests pass; Python changes also pass `python -m compileall packages tests`.
|
||||
- `git diff --check` passes.
|
||||
- Default tests are model-download-free, API-credit-free, and GPU-free.
|
||||
- Evidence README records exact changed files, commands/results, limitations, and dependency handoff; no fabricated evidence or inherited completion credit.
|
||||
- Native changes pass focused out-of-tree CMake build and CTest; patch changes verify clean apply/check/reverse against the exact llama.cpp pin.
|
||||
- Runs are opt-in and record exact artifact/split hashes, runtime/upstream pin, backend/driver, hardware, network, commands, and raw metrics. Model artifacts use configured mounted-drive storage and never `/home`.
|
||||
- Preserve existing Transformers behavior and backend-agnostic Tracker routing/load balancing/billing/relay semantics unless an explicit versioned contract says otherwise. One scoped story commit is expected during execution, but this specification-materialization change is not committed.
|
||||
|
||||
## Evidence handoff
|
||||
|
||||
Write and verify `.scratch/distributed-gguf-runtime/evidence/DGR-020/README.md`. Until every criterion and applicable gate has real evidence, this story remains `passes: false`. Legacy evidence is provenance only, not completion credit.
|
||||
@@ -0,0 +1,39 @@
|
||||
<!-- GENERATED FROM prd.json — DO NOT EDIT AS AN INDEPENDENT SOURCE. prd.json IS AUTHORITATIVE. -->
|
||||
# DGR-021: Define the versioned named-tensor stream envelope
|
||||
|
||||
- **Status / triage:** specification only; `ready-for-agent`; `passes: false`
|
||||
- **Execution mode:** `AFK`
|
||||
- **Milestone:** `M1`
|
||||
- **Dependencies:** `DGR-018`
|
||||
- **Blocks (derived):** `DGR-022`, `DGR-023`, `DGR-025`, `DGR-031`, `DGR-035`, `DGR-046`
|
||||
- **Labels:** `area:protocol`, `type:infrastructure`, `priority:p0`, `ready-for-agent`
|
||||
- **Evidence class:** `model-free`
|
||||
- **Hardware:** `none`
|
||||
- **Model:** `generic`
|
||||
- **Upstream:** `no`
|
||||
|
||||
## Objective / description
|
||||
|
||||
Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`, source issue `.scratch/distributed-gguf-runtime/issues/021-define-the-versioned-named-tensor-stream-envelope.md`, and evidence READMEs for dependencies (DGR-018) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Establish the backend-neutral protobuf envelope used by direct and relayed Shard activation traffic.
|
||||
|
||||
## Acceptance criteria
|
||||
|
||||
- [ ] Define schema version, request/work ID, route session/epoch, shard range/effective start, phase, position, and idempotency step.
|
||||
- [ ] Define named tensors with shape, dtype, byte order, bounded fragments, compression identity, and checksum.
|
||||
- [ ] Reserve extensible fields for token-ID sidebands, architecture state, recurrent state, and MTP without claiming implementations.
|
||||
- [ ] Add deterministic serialization, fragmentation, checksum, unknown-field, and size-limit tests.
|
||||
- [ ] Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff.
|
||||
|
||||
## Shared quality gates
|
||||
|
||||
- Targeted deterministic tests pass; Python changes also pass `python -m compileall packages tests`.
|
||||
- `git diff --check` passes.
|
||||
- Default tests are model-download-free, API-credit-free, and GPU-free.
|
||||
- Evidence README records exact changed files, commands/results, limitations, and dependency handoff; no fabricated evidence or inherited completion credit.
|
||||
- Native changes pass focused out-of-tree CMake build and CTest; patch changes verify clean apply/check/reverse against the exact llama.cpp pin.
|
||||
- Runs are opt-in and record exact artifact/split hashes, runtime/upstream pin, backend/driver, hardware, network, commands, and raw metrics. Model artifacts use configured mounted-drive storage and never `/home`.
|
||||
- Preserve existing Transformers behavior and backend-agnostic Tracker routing/load balancing/billing/relay semantics unless an explicit versioned contract says otherwise. One scoped story commit is expected during execution, but this specification-materialization change is not committed.
|
||||
|
||||
## Evidence handoff
|
||||
|
||||
Write and verify `.scratch/distributed-gguf-runtime/evidence/DGR-021/README.md`. Until every criterion and applicable gate has real evidence, this story remains `passes: false`. Legacy evidence is provenance only, not completion credit.
|
||||
@@ -0,0 +1,39 @@
|
||||
<!-- GENERATED FROM prd.json — DO NOT EDIT AS AN INDEPENDENT SOURCE. prd.json IS AUTHORITATIVE. -->
|
||||
# DGR-022: Define Shard lifecycle and structured status RPCs
|
||||
|
||||
- **Status / triage:** specification only; `ready-for-agent`; `passes: false`
|
||||
- **Execution mode:** `AFK`
|
||||
- **Milestone:** `M1`
|
||||
- **Dependencies:** `DGR-021`
|
||||
- **Blocks (derived):** `DGR-024`, `DGR-033`, `DGR-037`
|
||||
- **Labels:** `area:protocol`, `area:lifecycle`, `type:infrastructure`, `priority:p0`, `ready-for-agent`
|
||||
- **Evidence class:** `model-free`
|
||||
- **Hardware:** `none`
|
||||
- **Model:** `generic`
|
||||
- **Upstream:** `no`
|
||||
|
||||
## Objective / description
|
||||
|
||||
Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`, source issue `.scratch/distributed-gguf-runtime/issues/022-define-shard-lifecycle-and-structured-status-rpcs.md`, and evidence READMEs for dependencies (DGR-021) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Complete the gRPC contract for worker capability, health, sessions, cancellation, release, and metrics.
|
||||
|
||||
## Acceptance criteria
|
||||
|
||||
- [ ] Define capability, health, bidirectional session stream, cancellation, release, and metrics RPCs.
|
||||
- [ ] Specify deadlines, cancellation propagation, bounded flow control, cache expectations/results, and structured error taxonomy.
|
||||
- [ ] Specify TLS/auth hooks without moving Meshnet authentication or billing into the worker.
|
||||
- [ ] Add compatibility tests for supported versions and fail-closed tests for unsupported versions and malformed lifecycle transitions.
|
||||
- [ ] Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff.
|
||||
|
||||
## Shared quality gates
|
||||
|
||||
- Targeted deterministic tests pass; Python changes also pass `python -m compileall packages tests`.
|
||||
- `git diff --check` passes.
|
||||
- Default tests are model-download-free, API-credit-free, and GPU-free.
|
||||
- Evidence README records exact changed files, commands/results, limitations, and dependency handoff; no fabricated evidence or inherited completion credit.
|
||||
- Native changes pass focused out-of-tree CMake build and CTest; patch changes verify clean apply/check/reverse against the exact llama.cpp pin.
|
||||
- Runs are opt-in and record exact artifact/split hashes, runtime/upstream pin, backend/driver, hardware, network, commands, and raw metrics. Model artifacts use configured mounted-drive storage and never `/home`.
|
||||
- Preserve existing Transformers behavior and backend-agnostic Tracker routing/load balancing/billing/relay semantics unless an explicit versioned contract says otherwise. One scoped story commit is expected during execution, but this specification-materialization change is not committed.
|
||||
|
||||
## Evidence handoff
|
||||
|
||||
Write and verify `.scratch/distributed-gguf-runtime/evidence/DGR-022/README.md`. Until every criterion and applicable gate has real evidence, this story remains `passes: false`. Legacy evidence is provenance only, not completion credit.
|
||||
@@ -0,0 +1,39 @@
|
||||
<!-- GENERATED FROM prd.json — DO NOT EDIT AS AN INDEPENDENT SOURCE. prd.json IS AUTHORITATIVE. -->
|
||||
# DGR-023: Make Python and C++ protobuf generation reproducible
|
||||
|
||||
- **Status / triage:** specification only; `ready-for-agent`; `passes: false`
|
||||
- **Execution mode:** `AFK`
|
||||
- **Milestone:** `M1`
|
||||
- **Dependencies:** `DGR-021`
|
||||
- **Blocks (derived):** `DGR-024`, `DGR-037`
|
||||
- **Labels:** `area:protocol`, `area:build`, `type:tooling`, `priority:p0`, `ready-for-agent`
|
||||
- **Evidence class:** `model-free`
|
||||
- **Hardware:** `none`
|
||||
- **Model:** `generic`
|
||||
- **Upstream:** `no`
|
||||
|
||||
## Objective / description
|
||||
|
||||
Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`, source issue `.scratch/distributed-gguf-runtime/issues/023-make-python-and-c-protobuf-generation-reproducible.md`, and evidence READMEs for dependencies (DGR-021) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Generate identical Python/C++ protocol bindings without manual copying or checked-in build debris.
|
||||
|
||||
## Acceptance criteria
|
||||
|
||||
- [ ] Pin protoc, gRPC, and plugin versions or declare a verified compatible range.
|
||||
- [ ] Generate Python and C++ bindings into out-of-tree build/package locations through documented commands.
|
||||
- [ ] Add Python↔C++ round-trip and descriptor compatibility tests.
|
||||
- [ ] A clean checkout regenerates bindings deterministically or fails with an actionable toolchain error.
|
||||
- [ ] Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff.
|
||||
|
||||
## Shared quality gates
|
||||
|
||||
- Targeted deterministic tests pass; Python changes also pass `python -m compileall packages tests`.
|
||||
- `git diff --check` passes.
|
||||
- Default tests are model-download-free, API-credit-free, and GPU-free.
|
||||
- Evidence README records exact changed files, commands/results, limitations, and dependency handoff; no fabricated evidence or inherited completion credit.
|
||||
- Native changes pass focused out-of-tree CMake build and CTest; patch changes verify clean apply/check/reverse against the exact llama.cpp pin.
|
||||
- Runs are opt-in and record exact artifact/split hashes, runtime/upstream pin, backend/driver, hardware, network, commands, and raw metrics. Model artifacts use configured mounted-drive storage and never `/home`.
|
||||
- Preserve existing Transformers behavior and backend-agnostic Tracker routing/load balancing/billing/relay semantics unless an explicit versioned contract says otherwise. One scoped story commit is expected during execution, but this specification-materialization change is not committed.
|
||||
|
||||
## Evidence handoff
|
||||
|
||||
Write and verify `.scratch/distributed-gguf-runtime/evidence/DGR-023/README.md`. Until every criterion and applicable gate has real evidence, this story remains `passes: false`. Legacy evidence is provenance only, not completion credit.
|
||||
@@ -0,0 +1,39 @@
|
||||
<!-- GENERATED FROM prd.json — DO NOT EDIT AS AN INDEPENDENT SOURCE. prd.json IS AUTHORITATIVE. -->
|
||||
# DGR-024: Implement in-memory fake gRPC seam transport
|
||||
|
||||
- **Status / triage:** specification only; `ready-for-agent`; `passes: false`
|
||||
- **Execution mode:** `AFK`
|
||||
- **Milestone:** `M1`
|
||||
- **Dependencies:** `DGR-022`, `DGR-023`
|
||||
- **Blocks (derived):** `DGR-033`, `DGR-042`
|
||||
- **Labels:** `area:protocol`, `area:testing`, `type:vertical-slice`, `priority:p0`, `ready-for-agent`
|
||||
- **Evidence class:** `fixture`
|
||||
- **Hardware:** `none`
|
||||
- **Model:** `fake`
|
||||
- **Upstream:** `no`
|
||||
|
||||
## Objective / description
|
||||
|
||||
Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`, source issue `.scratch/distributed-gguf-runtime/issues/024-implement-in-memory-fake-grpc-seam-transport.md`, and evidence READMEs for dependencies (DGR-022, DGR-023) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Exercise the complete streaming protocol deterministically before a real model or worker exists.
|
||||
|
||||
## Acceptance criteria
|
||||
|
||||
- [ ] Provide a fake bidirectional stream supporting prefill fragments, decode fast-path frames, release, cancel, and structured errors.
|
||||
- [ ] Test flow-control blocking, deadlines, malformed fragments, checksum failure, duplicates, and stale epochs.
|
||||
- [ ] Verify direct and opaque-relay framing preserve identical protobuf bytes.
|
||||
- [ ] Tests require no sockets outside localhost, model downloads, or native accelerator.
|
||||
- [ ] Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff.
|
||||
|
||||
## Shared quality gates
|
||||
|
||||
- Targeted deterministic tests pass; Python changes also pass `python -m compileall packages tests`.
|
||||
- `git diff --check` passes.
|
||||
- Default tests are model-download-free, API-credit-free, and GPU-free.
|
||||
- Evidence README records exact changed files, commands/results, limitations, and dependency handoff; no fabricated evidence or inherited completion credit.
|
||||
- Native changes pass focused out-of-tree CMake build and CTest; patch changes verify clean apply/check/reverse against the exact llama.cpp pin.
|
||||
- Runs are opt-in and record exact artifact/split hashes, runtime/upstream pin, backend/driver, hardware, network, commands, and raw metrics. Model artifacts use configured mounted-drive storage and never `/home`.
|
||||
- Preserve existing Transformers behavior and backend-agnostic Tracker routing/load balancing/billing/relay semantics unless an explicit versioned contract says otherwise. One scoped story commit is expected during execution, but this specification-materialization change is not committed.
|
||||
|
||||
## Evidence handoff
|
||||
|
||||
Write and verify `.scratch/distributed-gguf-runtime/evidence/DGR-024/README.md`. Until every criterion and applicable gate has real evidence, this story remains `passes: false`. Legacy evidence is provenance only, not completion credit.
|
||||
@@ -0,0 +1,39 @@
|
||||
<!-- GENERATED FROM prd.json — DO NOT EDIT AS AN INDEPENDENT SOURCE. prd.json IS AUTHORITATIVE. -->
|
||||
# DGR-025: Define exact artifact and runtime recipe identity
|
||||
|
||||
- **Status / triage:** specification only; `ready-for-agent`; `passes: false`
|
||||
- **Execution mode:** `AFK`
|
||||
- **Milestone:** `M1`
|
||||
- **Dependencies:** `DGR-018`, `DGR-021`
|
||||
- **Blocks (derived):** `DGR-026`, `DGR-031`, `DGR-041`, `DGR-044`
|
||||
- **Labels:** `area:identity`, `area:admission`, `type:domain`, `priority:p0`, `ready-for-agent`
|
||||
- **Evidence class:** `model-free`
|
||||
- **Hardware:** `none`
|
||||
- **Model:** `generic`
|
||||
- **Upstream:** `no`
|
||||
|
||||
## Objective / description
|
||||
|
||||
Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`, source issue `.scratch/distributed-gguf-runtime/issues/025-define-exact-artifact-and-runtime-recipe-identity.md`, and evidence READMEs for dependencies (DGR-018, DGR-021) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Ensure the tracker and worker only combine numerically and operationally compatible shards.
|
||||
|
||||
## Acceptance criteria
|
||||
|
||||
- [ ] Fingerprint source artifact SHA, tokenizer revision, architecture adapter/version, boundary schema, runtime pin/patch stack, backend, quant, activation/compute dtype, and KV/state layout.
|
||||
- [ ] Bind each shard to an exact half-open range without hardcoding a topology or quant.
|
||||
- [ ] Fail closed on any artifact, adapter, boundary, cache, backend, or runtime mismatch.
|
||||
- [ ] Unsupported recipes remain registered-but-dark until real-hardware evidence certifies them.
|
||||
- [ ] Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff.
|
||||
|
||||
## Shared quality gates
|
||||
|
||||
- Targeted deterministic tests pass; Python changes also pass `python -m compileall packages tests`.
|
||||
- `git diff --check` passes.
|
||||
- Default tests are model-download-free, API-credit-free, and GPU-free.
|
||||
- Evidence README records exact changed files, commands/results, limitations, and dependency handoff; no fabricated evidence or inherited completion credit.
|
||||
- Native changes pass focused out-of-tree CMake build and CTest; patch changes verify clean apply/check/reverse against the exact llama.cpp pin.
|
||||
- Runs are opt-in and record exact artifact/split hashes, runtime/upstream pin, backend/driver, hardware, network, commands, and raw metrics. Model artifacts use configured mounted-drive storage and never `/home`.
|
||||
- Preserve existing Transformers behavior and backend-agnostic Tracker routing/load balancing/billing/relay semantics unless an explicit versioned contract says otherwise. One scoped story commit is expected during execution, but this specification-materialization change is not committed.
|
||||
|
||||
## Evidence handoff
|
||||
|
||||
Write and verify `.scratch/distributed-gguf-runtime/evidence/DGR-025/README.md`. Until every criterion and applicable gate has real evidence, this story remains `passes: false`. Legacy evidence is provenance only, not completion credit.
|
||||
@@ -0,0 +1,39 @@
|
||||
<!-- GENERATED FROM prd.json — DO NOT EDIT AS AN INDEPENDENT SOURCE. prd.json IS AUTHORITATIVE. -->
|
||||
# DGR-026: Provision exact split-GGUF artifacts outside /home
|
||||
|
||||
- **Status / triage:** specification only; `ready-for-agent`; `passes: false`
|
||||
- **Execution mode:** `AFK`
|
||||
- **Milestone:** `M1`
|
||||
- **Dependencies:** `DGR-025`
|
||||
- **Blocks (derived):** `DGR-044`, `DGR-045`
|
||||
- **Labels:** `area:artifacts`, `area:provenance`, `type:tooling`, `priority:p0`, `ready-for-agent`
|
||||
- **Evidence class:** `fixture`
|
||||
- **Hardware:** `none`
|
||||
- **Model:** `generic`
|
||||
- **Upstream:** `no`
|
||||
|
||||
## Objective / description
|
||||
|
||||
Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`, source issue `.scratch/distributed-gguf-runtime/issues/026-provision-exact-split-gguf-artifacts-outside-home.md`, and evidence READMEs for dependencies (DGR-025) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Make exact split-GGUF inputs reproducibly available from mounted-drive storage without embedding a quantization or topology assumption in product code.
|
||||
|
||||
## Acceptance criteria
|
||||
|
||||
- [ ] Create an exact manifest that binds the source artifact, tokenizer/revision, every split file name, size, range/role, and cryptographic hash.
|
||||
- [ ] Provide resumable, hash-verifying download/provision tooling targeting configured mounted-drive storage; refuse paths under `/home` and incomplete or mismatched splits.
|
||||
- [ ] Keep quantization and split topology as manifest/recipe inputs with no hardcoded quant, node count, or range layout.
|
||||
- [ ] Add deterministic model-download-free tests using tiny local split fixtures, including interrupted resume, missing split, hash mismatch, and `/home` rejection.
|
||||
- [ ] Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff.
|
||||
|
||||
## Shared quality gates
|
||||
|
||||
- Targeted deterministic tests pass; Python changes also pass `python -m compileall packages tests`.
|
||||
- `git diff --check` passes.
|
||||
- Default tests are model-download-free, API-credit-free, and GPU-free.
|
||||
- Evidence README records exact changed files, commands/results, limitations, and dependency handoff; no fabricated evidence or inherited completion credit.
|
||||
- Native changes pass focused out-of-tree CMake build and CTest; patch changes verify clean apply/check/reverse against the exact llama.cpp pin.
|
||||
- Runs are opt-in and record exact artifact/split hashes, runtime/upstream pin, backend/driver, hardware, network, commands, and raw metrics. Model artifacts use configured mounted-drive storage and never `/home`.
|
||||
- Preserve existing Transformers behavior and backend-agnostic Tracker routing/load balancing/billing/relay semantics unless an explicit versioned contract says otherwise. One scoped story commit is expected during execution, but this specification-materialization change is not committed.
|
||||
|
||||
## Evidence handoff
|
||||
|
||||
Write and verify `.scratch/distributed-gguf-runtime/evidence/DGR-026/README.md`. Until every criterion and applicable gate has real evidence, this story remains `passes: false`. Legacy evidence is provenance only, not completion credit.
|
||||
@@ -0,0 +1,39 @@
|
||||
<!-- GENERATED FROM prd.json — DO NOT EDIT AS AN INDEPENDENT SOURCE. prd.json IS AUTHORITATIVE. -->
|
||||
# DGR-027: Add exact llama.cpp provenance manifest and fetch workspace
|
||||
|
||||
- **Status / triage:** specification only; `ready-for-agent`; `passes: false`
|
||||
- **Execution mode:** `AFK`
|
||||
- **Milestone:** `M1`
|
||||
- **Dependencies:** `DGR-017`
|
||||
- **Blocks (derived):** `DGR-028`, `DGR-029`, `DGR-044`
|
||||
- **Labels:** `area:upstream`, `area:build`, `type:provenance`, `priority:p0`, `ready-for-agent`
|
||||
- **Evidence class:** `model-free`
|
||||
- **Hardware:** `none`
|
||||
- **Model:** `generic`
|
||||
- **Upstream:** `yes`
|
||||
|
||||
## Objective / description
|
||||
|
||||
Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`, source issue `.scratch/distributed-gguf-runtime/issues/027-add-exact-llama-cpp-provenance-manifest-and-fetch-workspace.md`, and evidence READMEs for dependencies (DGR-017) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Pin llama.cpp exactly through an in-repo manifest while fetching source only into an ignored build workspace.
|
||||
|
||||
## Acceptance criteria
|
||||
|
||||
- [ ] Manifest records upstream URL, exact commit, expected source archive/tree hash, license, and retrieval method.
|
||||
- [ ] Fetch tooling verifies identity before use and refuses an unpinned branch/tag.
|
||||
- [ ] Source is fetched into an ignored build workspace; no submodule, vendored source tree, or permanent fork is introduced.
|
||||
- [ ] Offline reuse is supported only after the cached tree’s exact identity is verified.
|
||||
- [ ] Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff.
|
||||
|
||||
## Shared quality gates
|
||||
|
||||
- Targeted deterministic tests pass; Python changes also pass `python -m compileall packages tests`.
|
||||
- `git diff --check` passes.
|
||||
- Default tests are model-download-free, API-credit-free, and GPU-free.
|
||||
- Evidence README records exact changed files, commands/results, limitations, and dependency handoff; no fabricated evidence or inherited completion credit.
|
||||
- Native changes pass focused out-of-tree CMake build and CTest; patch changes verify clean apply/check/reverse against the exact llama.cpp pin.
|
||||
- Runs are opt-in and record exact artifact/split hashes, runtime/upstream pin, backend/driver, hardware, network, commands, and raw metrics. Model artifacts use configured mounted-drive storage and never `/home`.
|
||||
- Preserve existing Transformers behavior and backend-agnostic Tracker routing/load balancing/billing/relay semantics unless an explicit versioned contract says otherwise. One scoped story commit is expected during execution, but this specification-materialization change is not committed.
|
||||
|
||||
## Evidence handoff
|
||||
|
||||
Write and verify `.scratch/distributed-gguf-runtime/evidence/DGR-027/README.md`. Until every criterion and applicable gate has real evidence, this story remains `passes: false`. Legacy evidence is provenance only, not completion credit.
|
||||
@@ -0,0 +1,39 @@
|
||||
<!-- GENERATED FROM prd.json — DO NOT EDIT AS AN INDEPENDENT SOURCE. prd.json IS AUTHORITATIVE. -->
|
||||
# DGR-028: Implement numbered patch-stack apply and verification
|
||||
|
||||
- **Status / triage:** specification only; `ready-for-agent`; `passes: false`
|
||||
- **Execution mode:** `AFK`
|
||||
- **Milestone:** `M1`
|
||||
- **Dependencies:** `DGR-027`
|
||||
- **Blocks (derived):** `DGR-029`, `DGR-034`, `DGR-069`
|
||||
- **Labels:** `area:upstream`, `area:patches`, `type:tooling`, `priority:p0`, `ready-for-agent`
|
||||
- **Evidence class:** `model-free`
|
||||
- **Hardware:** `none`
|
||||
- **Model:** `generic`
|
||||
- **Upstream:** `yes`
|
||||
|
||||
## Objective / description
|
||||
|
||||
Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`, source issue `.scratch/distributed-gguf-runtime/issues/028-implement-numbered-patch-stack-apply-and-verification.md`, and evidence READMEs for dependencies (DGR-027) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Maintain a minimal auditable llama.cpp delta with one numbered patch per concern.
|
||||
|
||||
## Acceptance criteria
|
||||
|
||||
- [ ] Add deterministic apply/check/reverse verification against the exact manifest pin.
|
||||
- [ ] Separate range loading, boundary I/O, filtered state, and worker hooks into scoped patches.
|
||||
- [ ] Record upstream file/API assumptions and fail with the first incompatible patch when the pin changes.
|
||||
- [ ] Verify license/attribution and prove no Meshnet routing, billing, relay, or authentication code enters the patch stack.
|
||||
- [ ] Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff.
|
||||
|
||||
## Shared quality gates
|
||||
|
||||
- Targeted deterministic tests pass; Python changes also pass `python -m compileall packages tests`.
|
||||
- `git diff --check` passes.
|
||||
- Default tests are model-download-free, API-credit-free, and GPU-free.
|
||||
- Evidence README records exact changed files, commands/results, limitations, and dependency handoff; no fabricated evidence or inherited completion credit.
|
||||
- Native changes pass focused out-of-tree CMake build and CTest; patch changes verify clean apply/check/reverse against the exact llama.cpp pin.
|
||||
- Runs are opt-in and record exact artifact/split hashes, runtime/upstream pin, backend/driver, hardware, network, commands, and raw metrics. Model artifacts use configured mounted-drive storage and never `/home`.
|
||||
- Preserve existing Transformers behavior and backend-agnostic Tracker routing/load balancing/billing/relay semantics unless an explicit versioned contract says otherwise. One scoped story commit is expected during execution, but this specification-materialization change is not committed.
|
||||
|
||||
## Evidence handoff
|
||||
|
||||
Write and verify `.scratch/distributed-gguf-runtime/evidence/DGR-028/README.md`. Until every criterion and applicable gate has real evidence, this story remains `passes: false`. Legacy evidence is provenance only, not completion credit.
|
||||
@@ -0,0 +1,39 @@
|
||||
<!-- GENERATED FROM prd.json — DO NOT EDIT AS AN INDEPENDENT SOURCE. prd.json IS AUTHORITATIVE. -->
|
||||
# DGR-029: Create the native CMake skeleton and deterministic CPU lane
|
||||
|
||||
- **Status / triage:** specification only; `ready-for-agent`; `passes: false`
|
||||
- **Execution mode:** `AFK`
|
||||
- **Milestone:** `M1`
|
||||
- **Dependencies:** `DGR-027`, `DGR-028`
|
||||
- **Blocks (derived):** `DGR-030`, `DGR-034`
|
||||
- **Labels:** `area:build`, `type:toolchain`, `priority:p0`, `ready-for-agent`
|
||||
- **Evidence class:** `model-free`
|
||||
- **Hardware:** `none`
|
||||
- **Model:** `generic`
|
||||
- **Upstream:** `yes`
|
||||
|
||||
## Objective / description
|
||||
|
||||
Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`, source issue `.scratch/distributed-gguf-runtime/issues/029-create-the-native-cmake-skeleton-and-deterministic-cpu-lane.md`, and evidence READMEs for dependencies (DGR-027, DGR-028) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Establish an out-of-tree standalone native build with a deterministic CPU lane before accelerator matrix work.
|
||||
|
||||
## Acceptance criteria
|
||||
|
||||
- [ ] Create the standalone native CMake target/skeleton and isolated out-of-tree configure/build preset for CPU.
|
||||
- [ ] Build and run a deterministic model-free CPU smoke/CTest lane from a clean checkout with actionable toolchain failures.
|
||||
- [ ] Keep fetched upstream sources, generated bindings, and all build outputs ignored and out of tree.
|
||||
- [ ] Ensure build success alone does not advertise any backend/model/recipe capability.
|
||||
- [ ] Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff.
|
||||
|
||||
## Shared quality gates
|
||||
|
||||
- Targeted deterministic tests pass; Python changes also pass `python -m compileall packages tests`.
|
||||
- `git diff --check` passes.
|
||||
- Default tests are model-download-free, API-credit-free, and GPU-free.
|
||||
- Evidence README records exact changed files, commands/results, limitations, and dependency handoff; no fabricated evidence or inherited completion credit.
|
||||
- Native changes pass focused out-of-tree CMake build and CTest; patch changes verify clean apply/check/reverse against the exact llama.cpp pin.
|
||||
- Runs are opt-in and record exact artifact/split hashes, runtime/upstream pin, backend/driver, hardware, network, commands, and raw metrics. Model artifacts use configured mounted-drive storage and never `/home`.
|
||||
- Preserve existing Transformers behavior and backend-agnostic Tracker routing/load balancing/billing/relay semantics unless an explicit versioned contract says otherwise. One scoped story commit is expected during execution, but this specification-materialization change is not committed.
|
||||
|
||||
## Evidence handoff
|
||||
|
||||
Write and verify `.scratch/distributed-gguf-runtime/evidence/DGR-029/README.md`. Until every criterion and applicable gate has real evidence, this story remains `passes: false`. Legacy evidence is provenance only, not completion credit.
|
||||
@@ -0,0 +1,39 @@
|
||||
<!-- GENERATED FROM prd.json — DO NOT EDIT AS AN INDEPENDENT SOURCE. prd.json IS AUTHORITATIVE. -->
|
||||
# DGR-030: Add accelerator build presets and native CI matrix
|
||||
|
||||
- **Status / triage:** specification only; `ready-for-agent`; `passes: false`
|
||||
- **Execution mode:** `AFK`
|
||||
- **Milestone:** `M1`
|
||||
- **Dependencies:** `DGR-029`
|
||||
- **Blocks (derived):** `DGR-053`, `DGR-067`, `DGR-068`
|
||||
- **Labels:** `area:build`, `area:hardware`, `type:toolchain`, `priority:p0`, `ready-for-agent`
|
||||
- **Evidence class:** `model-free`
|
||||
- **Hardware:** `optional`
|
||||
- **Model:** `generic`
|
||||
- **Upstream:** `yes`
|
||||
|
||||
## Objective / description
|
||||
|
||||
Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`, source issue `.scratch/distributed-gguf-runtime/issues/030-add-accelerator-build-presets-and-native-ci-matrix.md`, and evidence READMEs for dependencies (DGR-029) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Compile all required accelerator lanes reproducibly while keeping untested real-hardware capabilities registered-dark.
|
||||
|
||||
## Acceptance criteria
|
||||
|
||||
- [ ] Add isolated out-of-tree presets for CUDA, ROCm, Vulkan, and Metal without changing the deterministic CPU default.
|
||||
- [ ] Add a native CI/build matrix that reports unavailable SDKs as explicit unavailable/skipped lanes rather than false success.
|
||||
- [ ] Compile each available lane and preserve exact compiler, SDK, upstream pin, patch-stack, and build-option evidence.
|
||||
- [ ] Keep every backend/model/recipe lane registered-dark until a separate real-hardware certification record exists.
|
||||
- [ ] Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff.
|
||||
|
||||
## Shared quality gates
|
||||
|
||||
- Targeted deterministic tests pass; Python changes also pass `python -m compileall packages tests`.
|
||||
- `git diff --check` passes.
|
||||
- Default tests are model-download-free, API-credit-free, and GPU-free.
|
||||
- Evidence README records exact changed files, commands/results, limitations, and dependency handoff; no fabricated evidence or inherited completion credit.
|
||||
- Native changes pass focused out-of-tree CMake build and CTest; patch changes verify clean apply/check/reverse against the exact llama.cpp pin.
|
||||
- Runs are opt-in and record exact artifact/split hashes, runtime/upstream pin, backend/driver, hardware, network, commands, and raw metrics. Model artifacts use configured mounted-drive storage and never `/home`.
|
||||
- Preserve existing Transformers behavior and backend-agnostic Tracker routing/load balancing/billing/relay semantics unless an explicit versioned contract says otherwise. One scoped story commit is expected during execution, but this specification-materialization change is not committed.
|
||||
|
||||
## Evidence handoff
|
||||
|
||||
Write and verify `.scratch/distributed-gguf-runtime/evidence/DGR-030/README.md`. Until every criterion and applicable gate has real evidence, this story remains `passes: false`. Legacy evidence is provenance only, not completion credit.
|
||||
@@ -0,0 +1,39 @@
|
||||
<!-- GENERATED FROM prd.json — DO NOT EDIT AS AN INDEPENDENT SOURCE. prd.json IS AUTHORITATIVE. -->
|
||||
# DGR-031: Introduce the project-owned `ShardEngine` interface
|
||||
|
||||
- **Status / triage:** specification only; `ready-for-agent`; `passes: false`
|
||||
- **Execution mode:** `AFK`
|
||||
- **Milestone:** `M1`
|
||||
- **Dependencies:** `DGR-021`, `DGR-025`
|
||||
- **Blocks (derived):** `DGR-032`, `DGR-034`, `DGR-035`, `DGR-037`
|
||||
- **Labels:** `area:engine`, `type:architecture`, `priority:p0`, `ready-for-agent`
|
||||
- **Evidence class:** `model-free`
|
||||
- **Hardware:** `none`
|
||||
- **Model:** `generic`
|
||||
- **Upstream:** `no`
|
||||
|
||||
## Objective / description
|
||||
|
||||
Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`, source issue `.scratch/distributed-gguf-runtime/issues/031-introduce-the-project-owned-shardengine-interface.md`, and evidence READMEs for dependencies (DGR-021, DGR-025) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Isolate worker/protocol code from llama.cpp internals behind a stable project-owned engine contract.
|
||||
|
||||
## Acceptance criteria
|
||||
|
||||
- [ ] Define load, capabilities, prefill/decode, boundary/logits result, cancel, release, health, and metrics operations.
|
||||
- [ ] Use project-owned request/result/state types; expose no `ggml_tensor`, llama context, scheduler, or ABI-owned structure.
|
||||
- [ ] Reserve typed MTP and architecture auxiliary-state hooks without enabling them.
|
||||
- [ ] Add contract tests proving fake and future llama implementations obey identical lifecycle semantics.
|
||||
- [ ] Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff.
|
||||
|
||||
## Shared quality gates
|
||||
|
||||
- Targeted deterministic tests pass; Python changes also pass `python -m compileall packages tests`.
|
||||
- `git diff --check` passes.
|
||||
- Default tests are model-download-free, API-credit-free, and GPU-free.
|
||||
- Evidence README records exact changed files, commands/results, limitations, and dependency handoff; no fabricated evidence or inherited completion credit.
|
||||
- Native changes pass focused out-of-tree CMake build and CTest; patch changes verify clean apply/check/reverse against the exact llama.cpp pin.
|
||||
- Runs are opt-in and record exact artifact/split hashes, runtime/upstream pin, backend/driver, hardware, network, commands, and raw metrics. Model artifacts use configured mounted-drive storage and never `/home`.
|
||||
- Preserve existing Transformers behavior and backend-agnostic Tracker routing/load balancing/billing/relay semantics unless an explicit versioned contract says otherwise. One scoped story commit is expected during execution, but this specification-materialization change is not committed.
|
||||
|
||||
## Evidence handoff
|
||||
|
||||
Write and verify `.scratch/distributed-gguf-runtime/evidence/DGR-031/README.md`. Until every criterion and applicable gate has real evidence, this story remains `passes: false`. Legacy evidence is provenance only, not completion credit.
|
||||
@@ -0,0 +1,39 @@
|
||||
<!-- GENERATED FROM prd.json — DO NOT EDIT AS AN INDEPENDENT SOURCE. prd.json IS AUTHORITATIVE. -->
|
||||
# DGR-032: Implement deterministic fake `ShardEngine`
|
||||
|
||||
- **Status / triage:** specification only; `ready-for-agent`; `passes: false`
|
||||
- **Execution mode:** `AFK`
|
||||
- **Milestone:** `M1`
|
||||
- **Dependencies:** `DGR-031`
|
||||
- **Blocks (derived):** `DGR-033`
|
||||
- **Labels:** `area:engine`, `area:testing`, `type:fixture`, `priority:p0`, `ready-for-agent`
|
||||
- **Evidence class:** `fixture`
|
||||
- **Hardware:** `none`
|
||||
- **Model:** `fake`
|
||||
- **Upstream:** `no`
|
||||
|
||||
## Objective / description
|
||||
|
||||
Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`, source issue `.scratch/distributed-gguf-runtime/issues/032-implement-deterministic-fake-shardengine.md`, and evidence READMEs for dependencies (DGR-031) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Provide an engine fixture that deterministically transforms typed boundary bundles and session state.
|
||||
|
||||
## Acceptance criteria
|
||||
|
||||
- [ ] Support head, middle, tail, prefill, decode, cancellation, and release with deterministic outputs.
|
||||
- [ ] Model isolated session/epoch state and deterministic cache-miss/stale-epoch failures.
|
||||
- [ ] Support configurable delay, memory pressure, malformed output, and crash injection.
|
||||
- [ ] Contract tests distinguish fixture evidence from real-model certification.
|
||||
- [ ] Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff.
|
||||
|
||||
## Shared quality gates
|
||||
|
||||
- Targeted deterministic tests pass; Python changes also pass `python -m compileall packages tests`.
|
||||
- `git diff --check` passes.
|
||||
- Default tests are model-download-free, API-credit-free, and GPU-free.
|
||||
- Evidence README records exact changed files, commands/results, limitations, and dependency handoff; no fabricated evidence or inherited completion credit.
|
||||
- Native changes pass focused out-of-tree CMake build and CTest; patch changes verify clean apply/check/reverse against the exact llama.cpp pin.
|
||||
- Runs are opt-in and record exact artifact/split hashes, runtime/upstream pin, backend/driver, hardware, network, commands, and raw metrics. Model artifacts use configured mounted-drive storage and never `/home`.
|
||||
- Preserve existing Transformers behavior and backend-agnostic Tracker routing/load balancing/billing/relay semantics unless an explicit versioned contract says otherwise. One scoped story commit is expected during execution, but this specification-materialization change is not committed.
|
||||
|
||||
## Evidence handoff
|
||||
|
||||
Write and verify `.scratch/distributed-gguf-runtime/evidence/DGR-032/README.md`. Until every criterion and applicable gate has real evidence, this story remains `passes: false`. Legacy evidence is provenance only, not completion credit.
|
||||
@@ -0,0 +1,39 @@
|
||||
<!-- GENERATED FROM prd.json — DO NOT EDIT AS AN INDEPENDENT SOURCE. prd.json IS AUTHORITATIVE. -->
|
||||
# DGR-033: Build a standalone fake C++ gRPC Shard worker
|
||||
|
||||
- **Status / triage:** specification only; `ready-for-agent`; `passes: false`
|
||||
- **Execution mode:** `AFK`
|
||||
- **Milestone:** `M1`
|
||||
- **Dependencies:** `DGR-022`, `DGR-024`, `DGR-032`
|
||||
- **Blocks (derived):** `DGR-036`, `DGR-040`
|
||||
- **Labels:** `area:worker`, `area:grpc`, `type:vertical-slice`, `priority:p0`, `ready-for-agent`
|
||||
- **Evidence class:** `fixture`
|
||||
- **Hardware:** `none`
|
||||
- **Model:** `fake`
|
||||
- **Upstream:** `no`
|
||||
|
||||
## Objective / description
|
||||
|
||||
Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`, source issue `.scratch/distributed-gguf-runtime/issues/033-build-a-standalone-fake-c-grpc-shard-worker.md`, and evidence READMEs for dependencies (DGR-022, DGR-024, DGR-032) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Prove the standalone worker process, stream, lifecycle, and supervision shape before llama.cpp integration.
|
||||
|
||||
## Acceptance criteria
|
||||
|
||||
- [ ] A standalone C++ executable serves the complete lifecycle and stream RPC contract using the fake engine.
|
||||
- [ ] Python integration tests cover startup, health, capability, fragmented prefill, decode, release, cancellation, and graceful shutdown.
|
||||
- [ ] Bounded messages, deadlines, flow control, and independent session cancellation are enforced.
|
||||
- [ ] The worker exposes neither llama.cpp RPC nor arbitrary graph execution.
|
||||
- [ ] Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff.
|
||||
|
||||
## Shared quality gates
|
||||
|
||||
- Targeted deterministic tests pass; Python changes also pass `python -m compileall packages tests`.
|
||||
- `git diff --check` passes.
|
||||
- Default tests are model-download-free, API-credit-free, and GPU-free.
|
||||
- Evidence README records exact changed files, commands/results, limitations, and dependency handoff; no fabricated evidence or inherited completion credit.
|
||||
- Native changes pass focused out-of-tree CMake build and CTest; patch changes verify clean apply/check/reverse against the exact llama.cpp pin.
|
||||
- Runs are opt-in and record exact artifact/split hashes, runtime/upstream pin, backend/driver, hardware, network, commands, and raw metrics. Model artifacts use configured mounted-drive storage and never `/home`.
|
||||
- Preserve existing Transformers behavior and backend-agnostic Tracker routing/load balancing/billing/relay semantics unless an explicit versioned contract says otherwise. One scoped story commit is expected during execution, but this specification-materialization change is not committed.
|
||||
|
||||
## Evidence handoff
|
||||
|
||||
Write and verify `.scratch/distributed-gguf-runtime/evidence/DGR-033/README.md`. Until every criterion and applicable gate has real evidence, this story remains `passes: false`. Legacy evidence is provenance only, not completion credit.
|
||||
@@ -0,0 +1,39 @@
|
||||
<!-- GENERATED FROM prd.json — DO NOT EDIT AS AN INDEPENDENT SOURCE. prd.json IS AUTHORITATIVE. -->
|
||||
# DGR-034: Implement dense-Llama range-aware GGUF ownership
|
||||
|
||||
- **Status / triage:** specification only; `ready-for-agent`; `passes: false`
|
||||
- **Execution mode:** `AFK`
|
||||
- **Milestone:** `M2`
|
||||
- **Dependencies:** `DGR-028`, `DGR-029`, `DGR-031`
|
||||
- **Blocks (derived):** `DGR-035`, `DGR-037`, `DGR-051`
|
||||
- **Labels:** `area:llama`, `area:weights`, `type:runtime`, `priority:p0`, `ready-for-agent`
|
||||
- **Evidence class:** `real-model`
|
||||
- **Hardware:** `optional`
|
||||
- **Model:** `dense-llama`
|
||||
- **Upstream:** `yes`
|
||||
|
||||
## Objective / description
|
||||
|
||||
Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`, source issue `.scratch/distributed-gguf-runtime/issues/034-implement-dense-llama-range-aware-gguf-ownership.md`, and evidence READMEs for dependencies (DGR-028, DGR-029, DGR-031) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Load only the dense-Llama tensors owned by a shard range.
|
||||
|
||||
## Acceptance criteria
|
||||
|
||||
- [ ] Load only `blk.N.*` tensors in the assigned range, embeddings only at the head, and norm/output or tied output only at the tail.
|
||||
- [ ] Derive authoritative range and endpoint ownership from the loaded engine state.
|
||||
- [ ] Reject invalid/gapped/out-of-model ranges and unexpected required tensors.
|
||||
- [ ] Real-model evidence shows mapped/resident memory scales with owned tensors rather than full artifact size.
|
||||
- [ ] Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff.
|
||||
|
||||
## Shared quality gates
|
||||
|
||||
- Targeted deterministic tests pass; Python changes also pass `python -m compileall packages tests`.
|
||||
- `git diff --check` passes.
|
||||
- Default tests are model-download-free, API-credit-free, and GPU-free.
|
||||
- Evidence README records exact changed files, commands/results, limitations, and dependency handoff; no fabricated evidence or inherited completion credit.
|
||||
- Native changes pass focused out-of-tree CMake build and CTest; patch changes verify clean apply/check/reverse against the exact llama.cpp pin.
|
||||
- Runs are opt-in and record exact artifact/split hashes, runtime/upstream pin, backend/driver, hardware, network, commands, and raw metrics. Model artifacts use configured mounted-drive storage and never `/home`.
|
||||
- Preserve existing Transformers behavior and backend-agnostic Tracker routing/load balancing/billing/relay semantics unless an explicit versioned contract says otherwise. One scoped story commit is expected during execution, but this specification-materialization change is not committed.
|
||||
|
||||
## Evidence handoff
|
||||
|
||||
Write and verify `.scratch/distributed-gguf-runtime/evidence/DGR-034/README.md`. Until every criterion and applicable gate has real evidence, this story remains `passes: false`. Legacy evidence is provenance only, not completion credit.
|
||||
@@ -0,0 +1,39 @@
|
||||
<!-- GENERATED FROM prd.json — DO NOT EDIT AS AN INDEPENDENT SOURCE. prd.json IS AUTHORITATIVE. -->
|
||||
# DGR-035: Implement dense architecture boundary input/output
|
||||
|
||||
- **Status / triage:** specification only; `ready-for-agent`; `passes: false`
|
||||
- **Execution mode:** `AFK`
|
||||
- **Milestone:** `M2`
|
||||
- **Dependencies:** `DGR-021`, `DGR-031`, `DGR-034`
|
||||
- **Blocks (derived):** `DGR-036`, `DGR-037`, `DGR-069`
|
||||
- **Labels:** `area:llama`, `area:boundary`, `type:runtime`, `priority:p0`, `ready-for-agent`
|
||||
- **Evidence class:** `real-model`
|
||||
- **Hardware:** `optional`
|
||||
- **Model:** `dense-llama`
|
||||
- **Upstream:** `yes`
|
||||
|
||||
## Objective / description
|
||||
|
||||
Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`, source issue `.scratch/distributed-gguf-runtime/issues/035-implement-dense-architecture-boundary-input-output.md`, and evidence READMEs for dependencies (DGR-021, DGR-031, DGR-034) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Execute dense head/middle/tail ranges through an architecture-defined residual boundary.
|
||||
|
||||
## Acceptance criteria
|
||||
|
||||
- [ ] Head accepts token IDs and owns embedding; middle/tail bypass embedding and accept a named boundary bundle.
|
||||
- [ ] Non-tail returns the unnormalized residual before final norm/head and before tail-only row pruning.
|
||||
- [ ] Tail returns logits or sampled-token output under an explicit contract.
|
||||
- [ ] Uncertified architectures and incompatible boundary schemas fail closed.
|
||||
- [ ] Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff.
|
||||
|
||||
## Shared quality gates
|
||||
|
||||
- Targeted deterministic tests pass; Python changes also pass `python -m compileall packages tests`.
|
||||
- `git diff --check` passes.
|
||||
- Default tests are model-download-free, API-credit-free, and GPU-free.
|
||||
- Evidence README records exact changed files, commands/results, limitations, and dependency handoff; no fabricated evidence or inherited completion credit.
|
||||
- Native changes pass focused out-of-tree CMake build and CTest; patch changes verify clean apply/check/reverse against the exact llama.cpp pin.
|
||||
- Runs are opt-in and record exact artifact/split hashes, runtime/upstream pin, backend/driver, hardware, network, commands, and raw metrics. Model artifacts use configured mounted-drive storage and never `/home`.
|
||||
- Preserve existing Transformers behavior and backend-agnostic Tracker routing/load balancing/billing/relay semantics unless an explicit versioned contract says otherwise. One scoped story commit is expected during execution, but this specification-materialization change is not committed.
|
||||
|
||||
## Evidence handoff
|
||||
|
||||
Write and verify `.scratch/distributed-gguf-runtime/evidence/DGR-035/README.md`. Until every criterion and applicable gate has real evidence, this story remains `passes: false`. Legacy evidence is provenance only, not completion credit.
|
||||
@@ -0,0 +1,39 @@
|
||||
<!-- GENERATED FROM prd.json — DO NOT EDIT AS AN INDEPENDENT SOURCE. prd.json IS AUTHORITATIVE. -->
|
||||
# DGR-036: Prove dense fixture and real-model range parity
|
||||
|
||||
- **Status / triage:** specification only; `ready-for-agent`; `passes: false`
|
||||
- **Execution mode:** `AFK`
|
||||
- **Milestone:** `M2`
|
||||
- **Dependencies:** `DGR-033`, `DGR-035`
|
||||
- **Blocks (derived):** `DGR-039`
|
||||
- **Labels:** `area:parity`, `area:testing`, `type:certification`, `priority:p0`, `ready-for-agent`
|
||||
- **Evidence class:** `real-model`
|
||||
- **Hardware:** `optional`
|
||||
- **Model:** `dense-llama`
|
||||
- **Upstream:** `yes`
|
||||
|
||||
## Objective / description
|
||||
|
||||
Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`, source issue `.scratch/distributed-gguf-runtime/issues/036-prove-dense-fixture-and-real-model-range-parity.md`, and evidence READMEs for dependencies (DGR-033, DGR-035) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Prove the engine/protocol seam before adding session concurrency.
|
||||
|
||||
## Acceptance criteria
|
||||
|
||||
- [ ] Model-free two-stage tests pass through two fake worker processes with disjoint ranges.
|
||||
- [ ] A small real dense GGUF passes whole-model versus two-range prefill parity.
|
||||
- [ ] At least 32 greedy decode tokens match the locked tolerance.
|
||||
- [ ] Evidence distinguishes deterministic fixture proof from opt-in real-model proof.
|
||||
- [ ] Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff.
|
||||
|
||||
## Shared quality gates
|
||||
|
||||
- Targeted deterministic tests pass; Python changes also pass `python -m compileall packages tests`.
|
||||
- `git diff --check` passes.
|
||||
- Default tests are model-download-free, API-credit-free, and GPU-free.
|
||||
- Evidence README records exact changed files, commands/results, limitations, and dependency handoff; no fabricated evidence or inherited completion credit.
|
||||
- Native changes pass focused out-of-tree CMake build and CTest; patch changes verify clean apply/check/reverse against the exact llama.cpp pin.
|
||||
- Runs are opt-in and record exact artifact/split hashes, runtime/upstream pin, backend/driver, hardware, network, commands, and raw metrics. Model artifacts use configured mounted-drive storage and never `/home`.
|
||||
- Preserve existing Transformers behavior and backend-agnostic Tracker routing/load balancing/billing/relay semantics unless an explicit versioned contract says otherwise. One scoped story commit is expected during execution, but this specification-materialization change is not committed.
|
||||
|
||||
## Evidence handoff
|
||||
|
||||
Write and verify `.scratch/distributed-gguf-runtime/evidence/DGR-036/README.md`. Until every criterion and applicable gate has real evidence, this story remains `passes: false`. Legacy evidence is provenance only, not completion credit.
|
||||
@@ -0,0 +1,39 @@
|
||||
<!-- GENERATED FROM prd.json — DO NOT EDIT AS AN INDEPENDENT SOURCE. prd.json IS AUTHORITATIVE. -->
|
||||
# DGR-037: Bind llama.cpp to the standalone worker
|
||||
|
||||
- **Status / triage:** specification only; `ready-for-agent`; `passes: false`
|
||||
- **Execution mode:** `AFK`
|
||||
- **Milestone:** `M2`
|
||||
- **Dependencies:** `DGR-022`, `DGR-023`, `DGR-031`, `DGR-034`, `DGR-035`
|
||||
- **Blocks (derived):** `DGR-038`, `DGR-039`, `DGR-040`, `DGR-051`
|
||||
- **Labels:** `area:worker`, `area:llama`, `type:vertical-slice`, `priority:p0`, `ready-for-agent`
|
||||
- **Evidence class:** `real-model`
|
||||
- **Hardware:** `optional`
|
||||
- **Model:** `dense-llama`
|
||||
- **Upstream:** `yes`
|
||||
|
||||
## Objective / description
|
||||
|
||||
Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`, source issue `.scratch/distributed-gguf-runtime/issues/037-bind-llama-cpp-to-the-standalone-worker.md`, and evidence READMEs for dependencies (DGR-022, DGR-023, DGR-031, DGR-034, DGR-035) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Replace the fake engine with the pinned llama.cpp `ShardEngine` implementation without changing the public worker contract.
|
||||
|
||||
## Acceptance criteria
|
||||
|
||||
- [ ] Worker loads exactly one artifact/recipe/range identity and rejects mismatched stream requests.
|
||||
- [ ] All execution passes through `ShardEngine`; llama.cpp implementation types remain private.
|
||||
- [ ] Health and metrics expose loaded identity, authoritative ownership, memory, and execution state.
|
||||
- [ ] Graceful shutdown releases model/session resources; injected process death is observable and bounded.
|
||||
- [ ] Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff.
|
||||
|
||||
## Shared quality gates
|
||||
|
||||
- Targeted deterministic tests pass; Python changes also pass `python -m compileall packages tests`.
|
||||
- `git diff --check` passes.
|
||||
- Default tests are model-download-free, API-credit-free, and GPU-free.
|
||||
- Evidence README records exact changed files, commands/results, limitations, and dependency handoff; no fabricated evidence or inherited completion credit.
|
||||
- Native changes pass focused out-of-tree CMake build and CTest; patch changes verify clean apply/check/reverse against the exact llama.cpp pin.
|
||||
- Runs are opt-in and record exact artifact/split hashes, runtime/upstream pin, backend/driver, hardware, network, commands, and raw metrics. Model artifacts use configured mounted-drive storage and never `/home`.
|
||||
- Preserve existing Transformers behavior and backend-agnostic Tracker routing/load balancing/billing/relay semantics unless an explicit versioned contract says otherwise. One scoped story commit is expected during execution, but this specification-materialization change is not committed.
|
||||
|
||||
## Evidence handoff
|
||||
|
||||
Write and verify `.scratch/distributed-gguf-runtime/evidence/DGR-037/README.md`. Until every criterion and applicable gate has real evidence, this story remains `passes: false`. Legacy evidence is provenance only, not completion credit.
|
||||
@@ -0,0 +1,39 @@
|
||||
<!-- GENERATED FROM prd.json — DO NOT EDIT AS AN INDEPENDENT SOURCE. prd.json IS AUTHORITATIVE. -->
|
||||
# DGR-038: Implement isolated shard-local Hot KV State
|
||||
|
||||
- **Status / triage:** specification only; `ready-for-agent`; `passes: false`
|
||||
- **Execution mode:** `AFK`
|
||||
- **Milestone:** `M2`
|
||||
- **Dependencies:** `DGR-037`
|
||||
- **Blocks (derived):** `DGR-039`, `DGR-052`, `DGR-055`, `DGR-069`
|
||||
- **Labels:** `area:kv-cache`, `area:concurrency`, `type:runtime`, `priority:p0`, `ready-for-agent`
|
||||
- **Evidence class:** `real-model`
|
||||
- **Hardware:** `optional`
|
||||
- **Model:** `dense-llama`
|
||||
- **Upstream:** `yes`
|
||||
|
||||
## Objective / description
|
||||
|
||||
Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`, source issue `.scratch/distributed-gguf-runtime/issues/038-implement-isolated-shard-local-hot-kv-state.md`, and evidence READMEs for dependencies (DGR-037) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Map each route session and epoch to isolated state containing only locally owned layers.
|
||||
|
||||
## Acceptance criteria
|
||||
|
||||
- [ ] Map `(route_session_id, route_epoch)` to an isolated llama sequence or bounded context.
|
||||
- [ ] Support prefill/decode append, truncate, release, TTL/LRU eviction, cache miss, and stale-epoch rejection.
|
||||
- [ ] Four concurrent sessions complete without token, KV, position, or cancellation cross-talk.
|
||||
- [ ] Release/eviction returns memory to the configured budget without affecting other sessions.
|
||||
- [ ] Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff.
|
||||
|
||||
## Shared quality gates
|
||||
|
||||
- Targeted deterministic tests pass; Python changes also pass `python -m compileall packages tests`.
|
||||
- `git diff --check` passes.
|
||||
- Default tests are model-download-free, API-credit-free, and GPU-free.
|
||||
- Evidence README records exact changed files, commands/results, limitations, and dependency handoff; no fabricated evidence or inherited completion credit.
|
||||
- Native changes pass focused out-of-tree CMake build and CTest; patch changes verify clean apply/check/reverse against the exact llama.cpp pin.
|
||||
- Runs are opt-in and record exact artifact/split hashes, runtime/upstream pin, backend/driver, hardware, network, commands, and raw metrics. Model artifacts use configured mounted-drive storage and never `/home`.
|
||||
- Preserve existing Transformers behavior and backend-agnostic Tracker routing/load balancing/billing/relay semantics unless an explicit versioned contract says otherwise. One scoped story commit is expected during execution, but this specification-materialization change is not committed.
|
||||
|
||||
## Evidence handoff
|
||||
|
||||
Write and verify `.scratch/distributed-gguf-runtime/evidence/DGR-038/README.md`. Until every criterion and applicable gate has real evidence, this story remains `passes: false`. Legacy evidence is provenance only, not completion credit.
|
||||
@@ -0,0 +1,39 @@
|
||||
<!-- GENERATED FROM prd.json — DO NOT EDIT AS AN INDEPENDENT SOURCE. prd.json IS AUTHORITATIVE. -->
|
||||
# DGR-039: Pass local two-process dense acceptance
|
||||
|
||||
- **Status / triage:** specification only; `ready-for-agent`; `passes: false`
|
||||
- **Execution mode:** `AFK`
|
||||
- **Milestone:** `M2`
|
||||
- **Dependencies:** `DGR-036`, `DGR-037`, `DGR-038`
|
||||
- **Blocks (derived):** `DGR-054`
|
||||
- **Labels:** `area:integration`, `area:parity`, `type:certification`, `priority:p0`, `ready-for-agent`
|
||||
- **Evidence class:** `real-model`
|
||||
- **Hardware:** `optional`
|
||||
- **Model:** `dense-llama`
|
||||
- **Upstream:** `yes`
|
||||
|
||||
## Objective / description
|
||||
|
||||
Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`, source issue `.scratch/distributed-gguf-runtime/issues/039-pass-local-two-process-dense-acceptance.md`, and evidence READMEs for dependencies (DGR-036, DGR-037, DGR-038) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Establish the first real, independently executing distributed GGUF route on one host.
|
||||
|
||||
## Acceptance criteria
|
||||
|
||||
- [ ] Two worker processes open disjoint dense ranges and both execute real prefill/decode work.
|
||||
- [ ] Whole-model parity, 32-token greedy decode, four-session isolation, cancellation, and cleanup pass.
|
||||
- [ ] Record TTFT, prefill/decode rates, seam bytes/latency, RSS/VRAM, KV, queue, and failure metrics.
|
||||
- [ ] Killing one worker returns a bounded structured failure rather than hanging.
|
||||
- [ ] Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff.
|
||||
|
||||
## Shared quality gates
|
||||
|
||||
- Targeted deterministic tests pass; Python changes also pass `python -m compileall packages tests`.
|
||||
- `git diff --check` passes.
|
||||
- Default tests are model-download-free, API-credit-free, and GPU-free.
|
||||
- Evidence README records exact changed files, commands/results, limitations, and dependency handoff; no fabricated evidence or inherited completion credit.
|
||||
- Native changes pass focused out-of-tree CMake build and CTest; patch changes verify clean apply/check/reverse against the exact llama.cpp pin.
|
||||
- Runs are opt-in and record exact artifact/split hashes, runtime/upstream pin, backend/driver, hardware, network, commands, and raw metrics. Model artifacts use configured mounted-drive storage and never `/home`.
|
||||
- Preserve existing Transformers behavior and backend-agnostic Tracker routing/load balancing/billing/relay semantics unless an explicit versioned contract says otherwise. One scoped story commit is expected during execution, but this specification-materialization change is not committed.
|
||||
|
||||
## Evidence handoff
|
||||
|
||||
Write and verify `.scratch/distributed-gguf-runtime/evidence/DGR-039/README.md`. Until every criterion and applicable gate has real evidence, this story remains `passes: false`. Legacy evidence is provenance only, not completion credit.
|
||||
@@ -0,0 +1,39 @@
|
||||
<!-- GENERATED FROM prd.json — DO NOT EDIT AS AN INDEPENDENT SOURCE. prd.json IS AUTHORITATIVE. -->
|
||||
# DGR-040: Add node-side native worker supervision
|
||||
|
||||
- **Status / triage:** specification only; `ready-for-agent`; `passes: false`
|
||||
- **Execution mode:** `AFK`
|
||||
- **Milestone:** `M2`
|
||||
- **Dependencies:** `DGR-033`, `DGR-037`
|
||||
- **Blocks (derived):** `DGR-041`, `DGR-042`, `DGR-055`, `DGR-058`
|
||||
- **Labels:** `area:node`, `area:supervision`, `type:integration`, `priority:p0`, `ready-for-agent`
|
||||
- **Evidence class:** `fixture`
|
||||
- **Hardware:** `none`
|
||||
- **Model:** `generic`
|
||||
- **Upstream:** `no`
|
||||
|
||||
## Objective / description
|
||||
|
||||
Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`, source issue `.scratch/distributed-gguf-runtime/issues/040-add-node-side-native-worker-supervision.md`, and evidence READMEs for dependencies (DGR-033, DGR-037) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Let the existing node service safely start, probe, stop, and restart the standalone worker.
|
||||
|
||||
## Acceptance criteria
|
||||
|
||||
- [ ] Supervision owns process startup, readiness, log capture, graceful shutdown, and bounded forced termination.
|
||||
- [ ] Startup verifies worker binary, artifact identity, recipe, and range before registration.
|
||||
- [ ] Crashes or health loss make the capability unavailable without corrupting the Transformers backend.
|
||||
- [ ] Tests use the fake worker and deterministic crash injection.
|
||||
- [ ] Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff.
|
||||
|
||||
## Shared quality gates
|
||||
|
||||
- Targeted deterministic tests pass; Python changes also pass `python -m compileall packages tests`.
|
||||
- `git diff --check` passes.
|
||||
- Default tests are model-download-free, API-credit-free, and GPU-free.
|
||||
- Evidence README records exact changed files, commands/results, limitations, and dependency handoff; no fabricated evidence or inherited completion credit.
|
||||
- Native changes pass focused out-of-tree CMake build and CTest; patch changes verify clean apply/check/reverse against the exact llama.cpp pin.
|
||||
- Runs are opt-in and record exact artifact/split hashes, runtime/upstream pin, backend/driver, hardware, network, commands, and raw metrics. Model artifacts use configured mounted-drive storage and never `/home`.
|
||||
- Preserve existing Transformers behavior and backend-agnostic Tracker routing/load balancing/billing/relay semantics unless an explicit versioned contract says otherwise. One scoped story commit is expected during execution, but this specification-materialization change is not committed.
|
||||
|
||||
## Evidence handoff
|
||||
|
||||
Write and verify `.scratch/distributed-gguf-runtime/evidence/DGR-040/README.md`. Until every criterion and applicable gate has real evidence, this story remains `passes: false`. Legacy evidence is provenance only, not completion credit.
|
||||
@@ -0,0 +1,39 @@
|
||||
<!-- GENERATED FROM prd.json — DO NOT EDIT AS AN INDEPENDENT SOURCE. prd.json IS AUTHORITATIVE. -->
|
||||
# DGR-041: Register native Shard capabilities without redesigning Meshnet
|
||||
|
||||
- **Status / triage:** specification only; `ready-for-agent`; `passes: false`
|
||||
- **Execution mode:** `AFK`
|
||||
- **Milestone:** `M2`
|
||||
- **Dependencies:** `DGR-025`, `DGR-040`
|
||||
- **Blocks (derived):** `DGR-043`
|
||||
- **Labels:** `area:meshnet`, `area:admission`, `type:integration`, `priority:p0`, `ready-for-agent`
|
||||
- **Evidence class:** `model-free`
|
||||
- **Hardware:** `none`
|
||||
- **Model:** `generic`
|
||||
- **Upstream:** `no`
|
||||
|
||||
## Objective / description
|
||||
|
||||
Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`, source issue `.scratch/distributed-gguf-runtime/issues/041-register-native-shard-capabilities-without-redesigning-meshnet.md`, and evidence READMEs for dependencies (DGR-025, DGR-040) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Adapt native worker identity and capacity to existing backend-agnostic capability admission.
|
||||
|
||||
## Acceptance criteria
|
||||
|
||||
- [ ] Registration carries exact recipe fingerprint, authoritative range, backend, memory/KV capacity, concurrency, and certification status.
|
||||
- [ ] Existing tracker, billing, routing, telemetry, and provider semantics remain backend-agnostic.
|
||||
- [ ] Uncertified backend/model/recipe combinations are visible but unroutable.
|
||||
- [ ] Existing Transformers registration and route tests remain unchanged in behavior.
|
||||
- [ ] Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff.
|
||||
|
||||
## Shared quality gates
|
||||
|
||||
- Targeted deterministic tests pass; Python changes also pass `python -m compileall packages tests`.
|
||||
- `git diff --check` passes.
|
||||
- Default tests are model-download-free, API-credit-free, and GPU-free.
|
||||
- Evidence README records exact changed files, commands/results, limitations, and dependency handoff; no fabricated evidence or inherited completion credit.
|
||||
- Native changes pass focused out-of-tree CMake build and CTest; patch changes verify clean apply/check/reverse against the exact llama.cpp pin.
|
||||
- Runs are opt-in and record exact artifact/split hashes, runtime/upstream pin, backend/driver, hardware, network, commands, and raw metrics. Model artifacts use configured mounted-drive storage and never `/home`.
|
||||
- Preserve existing Transformers behavior and backend-agnostic Tracker routing/load balancing/billing/relay semantics unless an explicit versioned contract says otherwise. One scoped story commit is expected during execution, but this specification-materialization change is not committed.
|
||||
|
||||
## Evidence handoff
|
||||
|
||||
Write and verify `.scratch/distributed-gguf-runtime/evidence/DGR-041/README.md`. Until every criterion and applicable gate has real evidence, this story remains `passes: false`. Legacy evidence is provenance only, not completion credit.
|
||||
@@ -0,0 +1,39 @@
|
||||
<!-- GENERATED FROM prd.json — DO NOT EDIT AS AN INDEPENDENT SOURCE. prd.json IS AUTHORITATIVE. -->
|
||||
# DGR-042: Carry native frames through direct and existing relay seams
|
||||
|
||||
- **Status / triage:** specification only; `ready-for-agent`; `passes: false`
|
||||
- **Execution mode:** `AFK`
|
||||
- **Milestone:** `M2`
|
||||
- **Dependencies:** `DGR-024`, `DGR-040`
|
||||
- **Blocks (derived):** `DGR-054`, `DGR-058`
|
||||
- **Labels:** `area:meshnet`, `area:relay`, `area:grpc`, `type:integration`, `priority:p0`, `ready-for-agent`
|
||||
- **Evidence class:** `fixture`
|
||||
- **Hardware:** `none`
|
||||
- **Model:** `generic`
|
||||
- **Upstream:** `no`
|
||||
|
||||
## Objective / description
|
||||
|
||||
Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`, source issue `.scratch/distributed-gguf-runtime/issues/042-carry-native-frames-through-direct-and-existing-relay-seams.md`, and evidence READMEs for dependencies (DGR-024, DGR-040) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Use direct gRPC where available and the existing relay as opaque protobuf transport without redesigning relay behavior.
|
||||
|
||||
## Acceptance criteria
|
||||
|
||||
- [ ] Direct paths use the long-lived gRPC activation stream.
|
||||
- [ ] Relayed paths carry byte-identical versioned protobuf frames through the existing relay contract.
|
||||
- [ ] Request/work identity, cancellation, deadlines, telemetry, billing correlation, and per-node attribution survive both paths.
|
||||
- [ ] Fake-worker tests cover direct, relay, disconnect, cancellation, and bounded buffering.
|
||||
- [ ] Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff.
|
||||
|
||||
## Shared quality gates
|
||||
|
||||
- Targeted deterministic tests pass; Python changes also pass `python -m compileall packages tests`.
|
||||
- `git diff --check` passes.
|
||||
- Default tests are model-download-free, API-credit-free, and GPU-free.
|
||||
- Evidence README records exact changed files, commands/results, limitations, and dependency handoff; no fabricated evidence or inherited completion credit.
|
||||
- Native changes pass focused out-of-tree CMake build and CTest; patch changes verify clean apply/check/reverse against the exact llama.cpp pin.
|
||||
- Runs are opt-in and record exact artifact/split hashes, runtime/upstream pin, backend/driver, hardware, network, commands, and raw metrics. Model artifacts use configured mounted-drive storage and never `/home`.
|
||||
- Preserve existing Transformers behavior and backend-agnostic Tracker routing/load balancing/billing/relay semantics unless an explicit versioned contract says otherwise. One scoped story commit is expected during execution, but this specification-materialization change is not committed.
|
||||
|
||||
## Evidence handoff
|
||||
|
||||
Write and verify `.scratch/distributed-gguf-runtime/evidence/DGR-042/README.md`. Until every criterion and applicable gate has real evidence, this story remains `passes: false`. Legacy evidence is provenance only, not completion credit.
|
||||
@@ -0,0 +1,39 @@
|
||||
<!-- GENERATED FROM prd.json — DO NOT EDIT AS AN INDEPENDENT SOURCE. prd.json IS AUTHORITATIVE. -->
|
||||
# DGR-043: Expose GGUF compatibility and measured cost inputs to existing routing
|
||||
|
||||
- **Status / triage:** specification only; `ready-for-agent`; `passes: false`
|
||||
- **Execution mode:** `AFK`
|
||||
- **Milestone:** `M2`
|
||||
- **Dependencies:** `DGR-041`
|
||||
- **Blocks (derived):** `DGR-053`, `DGR-054`, `DGR-059`, `DGR-061`
|
||||
- **Labels:** `area:tracker`, `area:routing`, `type:integration`, `priority:p0`, `ready-for-agent`
|
||||
- **Evidence class:** `model-free`
|
||||
- **Hardware:** `none`
|
||||
- **Model:** `generic`
|
||||
- **Upstream:** `no`
|
||||
|
||||
## Objective / description
|
||||
|
||||
Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`, source issue `.scratch/distributed-gguf-runtime/issues/043-expose-gguf-compatibility-and-measured-cost-inputs-to-existing-routing.md`, and evidence READMEs for dependencies (DGR-041) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Adapt exact GGUF recipe/range compatibility and measured capacity, queue, seam-cost, health, and reliability data into the existing backend-agnostic routing inputs without redesigning routing or load balancing.
|
||||
|
||||
## Acceptance criteria
|
||||
|
||||
- [ ] Expose exact recipe, range coverage, capacity, queue/load, seam-cost, health, reliability, backend, and certification measurements through existing tracker input contracts.
|
||||
- [ ] Prove existing routing forms complete compatible coverage and excludes dark or mismatched candidates using its current backend-agnostic mechanisms.
|
||||
- [ ] Regression-test unchanged Transformers behavior and unchanged tracker routing, load-balancing, billing, relay, and provider semantics.
|
||||
- [ ] Regression-test that no quant, stage count, fixed split, architecture, backend sequence, or DeepSeek-specific policy is hardcoded.
|
||||
- [ ] Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff.
|
||||
|
||||
## Shared quality gates
|
||||
|
||||
- Targeted deterministic tests pass; Python changes also pass `python -m compileall packages tests`.
|
||||
- `git diff --check` passes.
|
||||
- Default tests are model-download-free, API-credit-free, and GPU-free.
|
||||
- Evidence README records exact changed files, commands/results, limitations, and dependency handoff; no fabricated evidence or inherited completion credit.
|
||||
- Native changes pass focused out-of-tree CMake build and CTest; patch changes verify clean apply/check/reverse against the exact llama.cpp pin.
|
||||
- Runs are opt-in and record exact artifact/split hashes, runtime/upstream pin, backend/driver, hardware, network, commands, and raw metrics. Model artifacts use configured mounted-drive storage and never `/home`.
|
||||
- Preserve existing Transformers behavior and backend-agnostic Tracker routing/load balancing/billing/relay semantics unless an explicit versioned contract says otherwise. One scoped story commit is expected during execution, but this specification-materialization change is not committed.
|
||||
|
||||
## Evidence handoff
|
||||
|
||||
Write and verify `.scratch/distributed-gguf-runtime/evidence/DGR-043/README.md`. Until every criterion and applicable gate has real evidence, this story remains `passes: false`. Legacy evidence is provenance only, not completion credit.
|
||||
@@ -0,0 +1,39 @@
|
||||
<!-- GENERATED FROM prd.json — DO NOT EDIT AS AN INDEPENDENT SOURCE. prd.json IS AUTHORITATIVE. -->
|
||||
# DGR-044: Pin the DeepSeek V4 Flash target contract
|
||||
|
||||
- **Status / triage:** specification only; `ready-for-agent`; `passes: false`
|
||||
- **Execution mode:** `AFK`
|
||||
- **Milestone:** `M3`
|
||||
- **Dependencies:** `DGR-019`, `DGR-025`, `DGR-026`, `DGR-027`
|
||||
- **Blocks (derived):** `DGR-045`
|
||||
- **Labels:** `area:deepseek-v4`, `area:provenance`, `type:contract`, `priority:p0`, `ready-for-agent`
|
||||
- **Evidence class:** `model-free`
|
||||
- **Hardware:** `none`
|
||||
- **Model:** `deepseek-v4-flash`
|
||||
- **Upstream:** `yes`
|
||||
|
||||
## Objective / description
|
||||
|
||||
Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`, source issue `.scratch/distributed-gguf-runtime/issues/044-pin-the-deepseek-v4-flash-target-contract.md`, and evidence READMEs for dependencies (DGR-019, DGR-025, DGR-026, DGR-027) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Fix the alpha/beta model identity and upstream maturity assumptions before implementing the adapter.
|
||||
|
||||
## Acceptance criteria
|
||||
|
||||
- [ ] Pin Hugging Face target SHA `60d8d70770c6776ff598c94bb586a859a38244f1`.
|
||||
- [ ] Record the selected GGUF provenance and exact source binding without assuming one quant.
|
||||
- [ ] Record that llama.cpp support began with PR 24162/commit `8c146a8` and remains maturing; the build manifest still pins one exact validated upstream commit.
|
||||
- [ ] Record 43 main layers plus MTP and all known architecture-specific state obligations.
|
||||
- [ ] Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff.
|
||||
|
||||
## Shared quality gates
|
||||
|
||||
- Targeted deterministic tests pass; Python changes also pass `python -m compileall packages tests`.
|
||||
- `git diff --check` passes.
|
||||
- Default tests are model-download-free, API-credit-free, and GPU-free.
|
||||
- Evidence README records exact changed files, commands/results, limitations, and dependency handoff; no fabricated evidence or inherited completion credit.
|
||||
- Native changes pass focused out-of-tree CMake build and CTest; patch changes verify clean apply/check/reverse against the exact llama.cpp pin.
|
||||
- Runs are opt-in and record exact artifact/split hashes, runtime/upstream pin, backend/driver, hardware, network, commands, and raw metrics. Model artifacts use configured mounted-drive storage and never `/home`.
|
||||
- Preserve existing Transformers behavior and backend-agnostic Tracker routing/load balancing/billing/relay semantics unless an explicit versioned contract says otherwise. One scoped story commit is expected during execution, but this specification-materialization change is not committed.
|
||||
|
||||
## Evidence handoff
|
||||
|
||||
Write and verify `.scratch/distributed-gguf-runtime/evidence/DGR-044/README.md`. Until every criterion and applicable gate has real evidence, this story remains `passes: false`. Legacy evidence is provenance only, not completion credit.
|
||||
@@ -0,0 +1,39 @@
|
||||
<!-- GENERATED FROM prd.json — DO NOT EDIT AS AN INDEPENDENT SOURCE. prd.json IS AUTHORITATIVE. -->
|
||||
# DGR-045: Inventory V4 GGUF tensors and layer ownership
|
||||
|
||||
- **Status / triage:** specification only; `ready-for-agent`; `passes: false`
|
||||
- **Execution mode:** `AFK`
|
||||
- **Milestone:** `M3`
|
||||
- **Dependencies:** `DGR-026`, `DGR-044`
|
||||
- **Blocks (derived):** `DGR-046`, `DGR-047`, `DGR-050`
|
||||
- **Labels:** `area:deepseek-v4`, `area:weights`, `type:research-spike`, `priority:p0`, `ready-for-agent`
|
||||
- **Evidence class:** `real-model`
|
||||
- **Hardware:** `none`
|
||||
- **Model:** `deepseek-v4-flash`
|
||||
- **Upstream:** `yes`
|
||||
|
||||
## Objective / description
|
||||
|
||||
Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`, source issue `.scratch/distributed-gguf-runtime/issues/045-inventory-v4-gguf-tensors-and-layer-ownership.md`, and evidence READMEs for dependencies (DGR-026, DGR-044) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Derive exact head, repeated-layer, tail, expert, auxiliary-state, and MTP ownership from the pinned artifact.
|
||||
|
||||
## Acceptance criteria
|
||||
|
||||
- [ ] Produce a machine-readable inventory tied to the target SHA and exact GGUF artifact.
|
||||
- [ ] Classify embeddings, 43 main layers, final head, MTP, mHC, attention variants, indexer/compressor, and MoE tensors.
|
||||
- [ ] Validate half-open range ownership and fail on unclassified required tensors.
|
||||
- [ ] Inventory tooling works across quants without embedding quant names in architecture logic.
|
||||
- [ ] Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff.
|
||||
|
||||
## Shared quality gates
|
||||
|
||||
- Targeted deterministic tests pass; Python changes also pass `python -m compileall packages tests`.
|
||||
- `git diff --check` passes.
|
||||
- Default tests are model-download-free, API-credit-free, and GPU-free.
|
||||
- Evidence README records exact changed files, commands/results, limitations, and dependency handoff; no fabricated evidence or inherited completion credit.
|
||||
- Native changes pass focused out-of-tree CMake build and CTest; patch changes verify clean apply/check/reverse against the exact llama.cpp pin.
|
||||
- Runs are opt-in and record exact artifact/split hashes, runtime/upstream pin, backend/driver, hardware, network, commands, and raw metrics. Model artifacts use configured mounted-drive storage and never `/home`.
|
||||
- Preserve existing Transformers behavior and backend-agnostic Tracker routing/load balancing/billing/relay semantics unless an explicit versioned contract says otherwise. One scoped story commit is expected during execution, but this specification-materialization change is not committed.
|
||||
|
||||
## Evidence handoff
|
||||
|
||||
Write and verify `.scratch/distributed-gguf-runtime/evidence/DGR-045/README.md`. Until every criterion and applicable gate has real evidence, this story remains `passes: false`. Legacy evidence is provenance only, not completion credit.
|
||||
@@ -0,0 +1,39 @@
|
||||
<!-- GENERATED FROM prd.json — DO NOT EDIT AS AN INDEPENDENT SOURCE. prd.json IS AUTHORITATIVE. -->
|
||||
# DGR-046: Define the V4 typed architecture boundary schema
|
||||
|
||||
- **Status / triage:** specification only; `ready-for-agent`; `passes: false`
|
||||
- **Execution mode:** `AFK`
|
||||
- **Milestone:** `M3`
|
||||
- **Dependencies:** `DGR-021`, `DGR-045`
|
||||
- **Blocks (derived):** `DGR-047`, `DGR-048`, `DGR-049`
|
||||
- **Labels:** `area:deepseek-v4`, `area:boundary`, `type:protocol`, `priority:p0`, `ready-for-agent`
|
||||
- **Evidence class:** `model-free`
|
||||
- **Hardware:** `none`
|
||||
- **Model:** `deepseek-v4-flash`
|
||||
- **Upstream:** `yes`
|
||||
|
||||
## Objective / description
|
||||
|
||||
Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`, source issue `.scratch/distributed-gguf-runtime/issues/046-define-the-v4-typed-architecture-boundary-schema.md`, and evidence READMEs for dependencies (DGR-021, DGR-045) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Define the exact cross-stage V4 architecture boundary while keeping per-layer attention and auxiliary caches shard-local.
|
||||
|
||||
## Acceptance criteria
|
||||
|
||||
- [ ] Define a versioned named bundle for the mHC 4×4096 residual boundary, positions, token-ID sideband where required, and schema/cache expectations.
|
||||
- [ ] Explicitly exclude per-layer CSA, HCA, SWA, indexer, compressor, KV, and MTP caches/state from the WAN boundary; those remain local to the owning shard and session/epoch.
|
||||
- [ ] Reserve typed MTP boundary fields but mark MTP execution unsupported and unroutable for alpha.
|
||||
- [ ] Fingerprint independently of quant/topology and fail closed on missing, incompatible, incorrectly shaped, or stale boundary/cache expectations.
|
||||
- [ ] Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff.
|
||||
|
||||
## Shared quality gates
|
||||
|
||||
- Targeted deterministic tests pass; Python changes also pass `python -m compileall packages tests`.
|
||||
- `git diff --check` passes.
|
||||
- Default tests are model-download-free, API-credit-free, and GPU-free.
|
||||
- Evidence README records exact changed files, commands/results, limitations, and dependency handoff; no fabricated evidence or inherited completion credit.
|
||||
- Native changes pass focused out-of-tree CMake build and CTest; patch changes verify clean apply/check/reverse against the exact llama.cpp pin.
|
||||
- Runs are opt-in and record exact artifact/split hashes, runtime/upstream pin, backend/driver, hardware, network, commands, and raw metrics. Model artifacts use configured mounted-drive storage and never `/home`.
|
||||
- Preserve existing Transformers behavior and backend-agnostic Tracker routing/load balancing/billing/relay semantics unless an explicit versioned contract says otherwise. One scoped story commit is expected during execution, but this specification-materialization change is not committed.
|
||||
|
||||
## Evidence handoff
|
||||
|
||||
Write and verify `.scratch/distributed-gguf-runtime/evidence/DGR-046/README.md`. Until every criterion and applicable gate has real evidence, this story remains `passes: false`. Legacy evidence is provenance only, not completion credit.
|
||||
@@ -0,0 +1,39 @@
|
||||
<!-- GENERATED FROM prd.json — DO NOT EDIT AS AN INDEPENDENT SOURCE. prd.json IS AUTHORITATIVE. -->
|
||||
# DGR-047: Adapt the upstream V4 mHC boundary for ranged ownership
|
||||
|
||||
- **Status / triage:** specification only; `ready-for-agent`; `passes: false`
|
||||
- **Execution mode:** `AFK`
|
||||
- **Milestone:** `M3`
|
||||
- **Dependencies:** `DGR-045`, `DGR-046`
|
||||
- **Blocks (derived):** `DGR-048`, `DGR-049`, `DGR-050`, `DGR-051`
|
||||
- **Labels:** `area:deepseek-v4`, `area:mhc`, `type:runtime`, `priority:p0`, `ready-for-agent`
|
||||
- **Evidence class:** `real-model`
|
||||
- **Hardware:** `optional`
|
||||
- **Model:** `deepseek-v4-flash`
|
||||
- **Upstream:** `yes`
|
||||
|
||||
## Objective / description
|
||||
|
||||
Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`, source issue `.scratch/distributed-gguf-runtime/issues/047-adapt-the-upstream-v4-mhc-boundary-for-ranged-ownership.md`, and evidence READMEs for dependencies (DGR-045, DGR-046) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Add range-boundary adapters around upstream llama.cpp V4 mHC execution without reimplementing the V4 graph or kernels.
|
||||
|
||||
## Acceptance criteria
|
||||
|
||||
- [ ] Represent and validate the upstream V4 4×4096 mHC boundary without flattening semantic axes.
|
||||
- [ ] Add only head/intermediate/tail range ownership and boundary conversion hooks around the pinned upstream llama.cpp graph.
|
||||
- [ ] Compare deterministic fixture vectors and single-process ranged outputs with upstream whole-model execution.
|
||||
- [ ] Document that llama.cpp owns V4 mHC graph/kernels and that quantized storage does not alter the logical boundary schema.
|
||||
- [ ] Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff.
|
||||
|
||||
## Shared quality gates
|
||||
|
||||
- Targeted deterministic tests pass; Python changes also pass `python -m compileall packages tests`.
|
||||
- `git diff --check` passes.
|
||||
- Default tests are model-download-free, API-credit-free, and GPU-free.
|
||||
- Evidence README records exact changed files, commands/results, limitations, and dependency handoff; no fabricated evidence or inherited completion credit.
|
||||
- Native changes pass focused out-of-tree CMake build and CTest; patch changes verify clean apply/check/reverse against the exact llama.cpp pin.
|
||||
- Runs are opt-in and record exact artifact/split hashes, runtime/upstream pin, backend/driver, hardware, network, commands, and raw metrics. Model artifacts use configured mounted-drive storage and never `/home`.
|
||||
- Preserve existing Transformers behavior and backend-agnostic Tracker routing/load balancing/billing/relay semantics unless an explicit versioned contract says otherwise. One scoped story commit is expected during execution, but this specification-materialization change is not committed.
|
||||
|
||||
## Evidence handoff
|
||||
|
||||
Write and verify `.scratch/distributed-gguf-runtime/evidence/DGR-047/README.md`. Until every criterion and applicable gate has real evidence, this story remains `passes: false`. Legacy evidence is provenance only, not completion credit.
|
||||
@@ -0,0 +1,39 @@
|
||||
<!-- GENERATED FROM prd.json — DO NOT EDIT AS AN INDEPENDENT SOURCE. prd.json IS AUTHORITATIVE. -->
|
||||
# DGR-048: Carry token-ID sideband through the first three hash-routed layers
|
||||
|
||||
- **Status / triage:** specification only; `ready-for-agent`; `passes: false`
|
||||
- **Execution mode:** `AFK`
|
||||
- **Milestone:** `M3`
|
||||
- **Dependencies:** `DGR-046`, `DGR-047`
|
||||
- **Blocks (derived):** `DGR-051`
|
||||
- **Labels:** `area:deepseek-v4`, `area:routing-state`, `type:runtime`, `priority:p0`, `ready-for-agent`
|
||||
- **Evidence class:** `real-model`
|
||||
- **Hardware:** `optional`
|
||||
- **Model:** `deepseek-v4-flash`
|
||||
- **Upstream:** `yes`
|
||||
|
||||
## Objective / description
|
||||
|
||||
Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`, source issue `.scratch/distributed-gguf-runtime/issues/048-carry-token-id-sideband-through-the-first-three-hash-routed-layers.md`, and evidence READMEs for dependencies (DGR-046, DGR-047) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Ensure any stage containing the first three hash-routed layers receives exact token identities.
|
||||
|
||||
## Acceptance criteria
|
||||
|
||||
- [ ] Head emits token IDs in the typed sideband for boundaries that require them.
|
||||
- [ ] Intermediate stages preserve or consume the sideband according to their layer range.
|
||||
- [ ] Routes splitting before, within, and after the first three layers pass deterministic partition tests.
|
||||
- [ ] Missing or mismatched token IDs fail closed rather than silently selecting incorrect experts.
|
||||
- [ ] Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff.
|
||||
|
||||
## Shared quality gates
|
||||
|
||||
- Targeted deterministic tests pass; Python changes also pass `python -m compileall packages tests`.
|
||||
- `git diff --check` passes.
|
||||
- Default tests are model-download-free, API-credit-free, and GPU-free.
|
||||
- Evidence README records exact changed files, commands/results, limitations, and dependency handoff; no fabricated evidence or inherited completion credit.
|
||||
- Native changes pass focused out-of-tree CMake build and CTest; patch changes verify clean apply/check/reverse against the exact llama.cpp pin.
|
||||
- Runs are opt-in and record exact artifact/split hashes, runtime/upstream pin, backend/driver, hardware, network, commands, and raw metrics. Model artifacts use configured mounted-drive storage and never `/home`.
|
||||
- Preserve existing Transformers behavior and backend-agnostic Tracker routing/load balancing/billing/relay semantics unless an explicit versioned contract says otherwise. One scoped story commit is expected during execution, but this specification-materialization change is not committed.
|
||||
|
||||
## Evidence handoff
|
||||
|
||||
Write and verify `.scratch/distributed-gguf-runtime/evidence/DGR-048/README.md`. Until every criterion and applicable gate has real evidence, this story remains `passes: false`. Legacy evidence is provenance only, not completion credit.
|
||||
@@ -0,0 +1,39 @@
|
||||
<!-- GENERATED FROM prd.json — DO NOT EDIT AS AN INDEPENDENT SOURCE. prd.json IS AUTHORITATIVE. -->
|
||||
# DGR-049: Keep V4 attention and auxiliary state shard-local
|
||||
|
||||
- **Status / triage:** specification only; `ready-for-agent`; `passes: false`
|
||||
- **Execution mode:** `AFK`
|
||||
- **Milestone:** `M3`
|
||||
- **Dependencies:** `DGR-046`, `DGR-047`
|
||||
- **Blocks (derived):** `DGR-051`
|
||||
- **Labels:** `area:deepseek-v4`, `area:attention`, `type:runtime`, `priority:p0`, `ready-for-agent`
|
||||
- **Evidence class:** `real-model`
|
||||
- **Hardware:** `optional`
|
||||
- **Model:** `deepseek-v4-flash`
|
||||
- **Upstream:** `yes`
|
||||
|
||||
## Objective / description
|
||||
|
||||
Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`, source issue `.scratch/distributed-gguf-runtime/issues/049-keep-v4-attention-and-auxiliary-state-shard-local.md`, and evidence READMEs for dependencies (DGR-046, DGR-047) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Bind V4 CSA/HCA/SWA/indexer/compressor and KV state to the owning shard session/epoch rather than transferring caches over the WAN.
|
||||
|
||||
## Acceptance criteria
|
||||
|
||||
- [ ] Map CSA, HCA, SWA, indexer, compressor, and KV ownership from the pinned upstream graph to each owned layer range.
|
||||
- [ ] Key all such caches/state by route session and epoch with bounded lifecycle, memory accounting, stale-epoch rejection, release, and eviction.
|
||||
- [ ] Prove cross-stage messages carry only the typed architecture boundary and cache expectations, never per-layer cache contents.
|
||||
- [ ] On route change or state loss, use explicit cache miss and re-prefill/restart; do not migrate V4 caches across workers.
|
||||
- [ ] Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff.
|
||||
|
||||
## Shared quality gates
|
||||
|
||||
- Targeted deterministic tests pass; Python changes also pass `python -m compileall packages tests`.
|
||||
- `git diff --check` passes.
|
||||
- Default tests are model-download-free, API-credit-free, and GPU-free.
|
||||
- Evidence README records exact changed files, commands/results, limitations, and dependency handoff; no fabricated evidence or inherited completion credit.
|
||||
- Native changes pass focused out-of-tree CMake build and CTest; patch changes verify clean apply/check/reverse against the exact llama.cpp pin.
|
||||
- Runs are opt-in and record exact artifact/split hashes, runtime/upstream pin, backend/driver, hardware, network, commands, and raw metrics. Model artifacts use configured mounted-drive storage and never `/home`.
|
||||
- Preserve existing Transformers behavior and backend-agnostic Tracker routing/load balancing/billing/relay semantics unless an explicit versioned contract says otherwise. One scoped story commit is expected during execution, but this specification-materialization change is not committed.
|
||||
|
||||
## Evidence handoff
|
||||
|
||||
Write and verify `.scratch/distributed-gguf-runtime/evidence/DGR-049/README.md`. Until every criterion and applicable gate has real evidence, this story remains `passes: false`. Legacy evidence is provenance only, not completion credit.
|
||||
@@ -0,0 +1,39 @@
|
||||
<!-- GENERATED FROM prd.json — DO NOT EDIT AS AN INDEPENDENT SOURCE. prd.json IS AUTHORITATIVE. -->
|
||||
# DGR-050: Validate upstream V4 MoE and hash-routing execution under ranged ownership
|
||||
|
||||
- **Status / triage:** specification only; `ready-for-agent`; `passes: false`
|
||||
- **Execution mode:** `AFK`
|
||||
- **Milestone:** `M3`
|
||||
- **Dependencies:** `DGR-045`, `DGR-047`
|
||||
- **Blocks (derived):** `DGR-051`
|
||||
- **Labels:** `area:deepseek-v4`, `area:moe`, `type:runtime`, `priority:p0`, `ready-for-agent`
|
||||
- **Evidence class:** `real-model`
|
||||
- **Hardware:** `optional`
|
||||
- **Model:** `deepseek-v4-flash`
|
||||
- **Upstream:** `yes`
|
||||
|
||||
## Objective / description
|
||||
|
||||
Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`, source issue `.scratch/distributed-gguf-runtime/issues/050-validate-upstream-v4-moe-and-hash-routing-execution-under-ranged-ownership.md`, and evidence READMEs for dependencies (DGR-045, DGR-047) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Validate the pinned upstream llama.cpp V4 MoE and hash-routing graph when layers are range-owned, without reimplementing routing or expert kernels in Meshnet.
|
||||
|
||||
## Acceptance criteria
|
||||
|
||||
- [ ] Load range-owned tensors for 256 routed plus one shared expert and validate upstream execution activates six routed experts where specified.
|
||||
- [ ] Validate the first three upstream hash-routed layers receive exact token-ID sideband across splits before, within, and after them.
|
||||
- [ ] Compare upstream whole-model and ranged router/expert outputs, shared-expert contribution, and malformed sideband failures.
|
||||
- [ ] Document that llama.cpp owns V4 MoE, attention, hash routing, graph, and kernels; no expert-parallel WAN collective or Meshnet reimplementation is introduced.
|
||||
- [ ] Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff.
|
||||
|
||||
## Shared quality gates
|
||||
|
||||
- Targeted deterministic tests pass; Python changes also pass `python -m compileall packages tests`.
|
||||
- `git diff --check` passes.
|
||||
- Default tests are model-download-free, API-credit-free, and GPU-free.
|
||||
- Evidence README records exact changed files, commands/results, limitations, and dependency handoff; no fabricated evidence or inherited completion credit.
|
||||
- Native changes pass focused out-of-tree CMake build and CTest; patch changes verify clean apply/check/reverse against the exact llama.cpp pin.
|
||||
- Runs are opt-in and record exact artifact/split hashes, runtime/upstream pin, backend/driver, hardware, network, commands, and raw metrics. Model artifacts use configured mounted-drive storage and never `/home`.
|
||||
- Preserve existing Transformers behavior and backend-agnostic Tracker routing/load balancing/billing/relay semantics unless an explicit versioned contract says otherwise. One scoped story commit is expected during execution, but this specification-materialization change is not committed.
|
||||
|
||||
## Evidence handoff
|
||||
|
||||
Write and verify `.scratch/distributed-gguf-runtime/evidence/DGR-050/README.md`. Until every criterion and applicable gate has real evidence, this story remains `passes: false`. Legacy evidence is provenance only, not completion credit.
|
||||
@@ -0,0 +1,39 @@
|
||||
<!-- GENERATED FROM prd.json — DO NOT EDIT AS AN INDEPENDENT SOURCE. prd.json IS AUTHORITATIVE. -->
|
||||
# DGR-051: Assemble the DeepSeek V4 Flash `ShardEngine` adapter
|
||||
|
||||
- **Status / triage:** specification only; `ready-for-agent`; `passes: false`
|
||||
- **Execution mode:** `AFK`
|
||||
- **Milestone:** `M3`
|
||||
- **Dependencies:** `DGR-034`, `DGR-037`, `DGR-047`, `DGR-048`, `DGR-049`, `DGR-050`
|
||||
- **Blocks (derived):** `DGR-052`, `DGR-060`, `DGR-065`, `DGR-069`
|
||||
- **Labels:** `area:deepseek-v4`, `area:engine`, `type:vertical-slice`, `priority:p0`, `ready-for-agent`
|
||||
- **Evidence class:** `real-model`
|
||||
- **Hardware:** `optional`
|
||||
- **Model:** `deepseek-v4-flash`
|
||||
- **Upstream:** `yes`
|
||||
|
||||
## Objective / description
|
||||
|
||||
Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`, source issue `.scratch/distributed-gguf-runtime/issues/051-assemble-the-deepseek-v4-flash-shardengine-adapter.md`, and evidence READMEs for dependencies (DGR-034, DGR-037, DGR-047, DGR-048, DGR-049, DGR-050) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Assemble range ownership hooks and boundary/local-state adapters around upstream llama.cpp V4 execution behind the stable ShardEngine interface.
|
||||
|
||||
## Acceptance criteria
|
||||
|
||||
- [ ] Support valid head, middle, tail, and whole-model ranges over all 43 main layers using the pinned upstream llama.cpp V4 graph/kernels.
|
||||
- [ ] Integrate exact range ownership, mHC boundary, positions, required token-ID sideband, and shard-local session/epoch state adapters.
|
||||
- [ ] Report MTP reserved-but-not-executable for alpha and reject unsupported split points or cache expectations.
|
||||
- [ ] Include exact adapter/schema/runtime/artifact identity and valid split restrictions without reimplementing V4 MoE, attention, mHC, or hash routing.
|
||||
- [ ] Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff.
|
||||
|
||||
## Shared quality gates
|
||||
|
||||
- Targeted deterministic tests pass; Python changes also pass `python -m compileall packages tests`.
|
||||
- `git diff --check` passes.
|
||||
- Default tests are model-download-free, API-credit-free, and GPU-free.
|
||||
- Evidence README records exact changed files, commands/results, limitations, and dependency handoff; no fabricated evidence or inherited completion credit.
|
||||
- Native changes pass focused out-of-tree CMake build and CTest; patch changes verify clean apply/check/reverse against the exact llama.cpp pin.
|
||||
- Runs are opt-in and record exact artifact/split hashes, runtime/upstream pin, backend/driver, hardware, network, commands, and raw metrics. Model artifacts use configured mounted-drive storage and never `/home`.
|
||||
- Preserve existing Transformers behavior and backend-agnostic Tracker routing/load balancing/billing/relay semantics unless an explicit versioned contract says otherwise. One scoped story commit is expected during execution, but this specification-materialization change is not committed.
|
||||
|
||||
## Evidence handoff
|
||||
|
||||
Write and verify `.scratch/distributed-gguf-runtime/evidence/DGR-051/README.md`. Until every criterion and applicable gate has real evidence, this story remains `passes: false`. Legacy evidence is provenance only, not completion credit.
|
||||
@@ -0,0 +1,39 @@
|
||||
<!-- GENERATED FROM prd.json — DO NOT EDIT AS AN INDEPENDENT SOURCE. prd.json IS AUTHORITATIVE. -->
|
||||
# DGR-052: Pass local V4 whole-model versus ranged parity
|
||||
|
||||
- **Status / triage:** specification only; `ready-for-agent`; `passes: false`
|
||||
- **Execution mode:** `AFK`
|
||||
- **Milestone:** `M3`
|
||||
- **Dependencies:** `DGR-038`, `DGR-051`
|
||||
- **Blocks (derived):** `DGR-053`, `DGR-054`
|
||||
- **Labels:** `area:deepseek-v4`, `area:parity`, `type:certification`, `priority:p0`, `ready-for-agent`
|
||||
- **Evidence class:** `real-model`
|
||||
- **Hardware:** `optional`
|
||||
- **Model:** `deepseek-v4-flash`
|
||||
- **Upstream:** `yes`
|
||||
|
||||
## Objective / description
|
||||
|
||||
Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`, source issue `.scratch/distributed-gguf-runtime/issues/052-pass-local-v4-whole-model-versus-ranged-parity.md`, and evidence READMEs for dependencies (DGR-038, DGR-051) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Prove V4 prefill and decode correctness locally before network certification.
|
||||
|
||||
## Acceptance criteria
|
||||
|
||||
- [ ] Compare pinned whole-model llama.cpp with at least two valid ranged partitions.
|
||||
- [ ] Prefill intermediates and locked-length greedy decode pass architecture-specific tolerances.
|
||||
- [ ] Test splits around the first three hash-routed layers and at least one CSA/HCA/SWA/indexer/compressor transition.
|
||||
- [ ] Four concurrent sessions pass KV/state isolation and cleanup.
|
||||
- [ ] Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff.
|
||||
|
||||
## Shared quality gates
|
||||
|
||||
- Targeted deterministic tests pass; Python changes also pass `python -m compileall packages tests`.
|
||||
- `git diff --check` passes.
|
||||
- Default tests are model-download-free, API-credit-free, and GPU-free.
|
||||
- Evidence README records exact changed files, commands/results, limitations, and dependency handoff; no fabricated evidence or inherited completion credit.
|
||||
- Native changes pass focused out-of-tree CMake build and CTest; patch changes verify clean apply/check/reverse against the exact llama.cpp pin.
|
||||
- Runs are opt-in and record exact artifact/split hashes, runtime/upstream pin, backend/driver, hardware, network, commands, and raw metrics. Model artifacts use configured mounted-drive storage and never `/home`.
|
||||
- Preserve existing Transformers behavior and backend-agnostic Tracker routing/load balancing/billing/relay semantics unless an explicit versioned contract says otherwise. One scoped story commit is expected during execution, but this specification-materialization change is not committed.
|
||||
|
||||
## Evidence handoff
|
||||
|
||||
Write and verify `.scratch/distributed-gguf-runtime/evidence/DGR-052/README.md`. Until every criterion and applicable gate has real evidence, this story remains `passes: false`. Legacy evidence is provenance only, not completion credit.
|
||||
@@ -0,0 +1,40 @@
|
||||
<!-- GENERATED FROM prd.json — DO NOT EDIT AS AN INDEPENDENT SOURCE. prd.json IS AUTHORITATIVE. -->
|
||||
# DGR-053: Certify a real 2–4-stage V4 route
|
||||
|
||||
- **Status / triage:** specification only; `ready-for-human`; `passes: false`
|
||||
- **Execution mode:** `HITL`
|
||||
- **Milestone:** `M3`
|
||||
- **Dependencies:** `DGR-030`, `DGR-043`, `DGR-052`
|
||||
- **Blocks (derived):** `DGR-054`, `DGR-062`, `DGR-067`
|
||||
- **Labels:** `area:deepseek-v4`, `area:hardware`, `type:certification`, `priority:p0`, `gate:hitl`, `ready-for-human`
|
||||
- **Evidence class:** `real-hardware`
|
||||
- **Hardware:** `required`
|
||||
- **Model:** `deepseek-v4-flash`
|
||||
- **Upstream:** `yes`
|
||||
|
||||
## Objective / description
|
||||
|
||||
Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`, source issue `.scratch/distributed-gguf-runtime/issues/053-certify-a-real-2-4-stage-v4-route.md`, and evidence READMEs for dependencies (DGR-030, DGR-043, DGR-052) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Prove real Tracker-selected V4 execution across physical machines before alpha.
|
||||
|
||||
## Acceptance criteria
|
||||
|
||||
- [ ] Run one documented 2–4-stage certification scenario using exact compatible artifacts/recipes; the count and chosen quant are evidence inputs, not product constants.
|
||||
- [ ] Actual CPU/GPU work executes on every stage; fake workers do not satisfy acceptance.
|
||||
- [ ] Record parity, TTFT, prefill/decode speed, seam cost, memory, cache/state isolation, cancellation, and cleanup.
|
||||
- [ ] Tracker selection remains dynamic and rejects an injected incompatible backend/recipe.
|
||||
- [ ] Only the exact real-hardware lanes exercised become eligible for advertisement.
|
||||
- [ ] Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff.
|
||||
|
||||
## Shared quality gates
|
||||
|
||||
- Targeted deterministic tests pass; Python changes also pass `python -m compileall packages tests`.
|
||||
- `git diff --check` passes.
|
||||
- Default tests are model-download-free, API-credit-free, and GPU-free.
|
||||
- Evidence README records exact changed files, commands/results, limitations, and dependency handoff; no fabricated evidence or inherited completion credit.
|
||||
- Native changes pass focused out-of-tree CMake build and CTest; patch changes verify clean apply/check/reverse against the exact llama.cpp pin.
|
||||
- Runs are opt-in and record exact artifact/split hashes, runtime/upstream pin, backend/driver, hardware, network, commands, and raw metrics. Model artifacts use configured mounted-drive storage and never `/home`.
|
||||
- Preserve existing Transformers behavior and backend-agnostic Tracker routing/load balancing/billing/relay semantics unless an explicit versioned contract says otherwise. One scoped story commit is expected during execution, but this specification-materialization change is not committed.
|
||||
|
||||
## Evidence handoff
|
||||
|
||||
Write and verify `.scratch/distributed-gguf-runtime/evidence/DGR-053/README.md`. Until every criterion and applicable gate has real evidence, this story remains `passes: false`. Legacy evidence is provenance only, not completion credit.
|
||||
@@ -0,0 +1,39 @@
|
||||
<!-- GENERATED FROM prd.json — DO NOT EDIT AS AN INDEPENDENT SOURCE. prd.json IS AUTHORITATIVE. -->
|
||||
# DGR-054: Enforce the DeepSeek V4 Flash alpha gate
|
||||
|
||||
- **Status / triage:** specification only; `ready-for-human`; `passes: false`
|
||||
- **Execution mode:** `HITL`
|
||||
- **Milestone:** `M3`
|
||||
- **Dependencies:** `DGR-017`, `DGR-019`, `DGR-020`, `DGR-039`, `DGR-042`, `DGR-043`, `DGR-052`, `DGR-053`
|
||||
- **Blocks (derived):** `DGR-055`, `DGR-065`, `DGR-066`, `DGR-068`
|
||||
- **Labels:** `area:deepseek-v4`, `area:release`, `milestone:alpha`, `priority:p0`, `gate:hitl`, `ready-for-human`
|
||||
- **Evidence class:** `release`
|
||||
- **Hardware:** `required`
|
||||
- **Model:** `deepseek-v4-flash`
|
||||
- **Upstream:** `yes`
|
||||
|
||||
## Objective / description
|
||||
|
||||
Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`, source issue `.scratch/distributed-gguf-runtime/issues/054-enforce-the-deepseek-v4-flash-alpha-gate.md`, and evidence READMEs for dependencies (DGR-017, DGR-019, DGR-020, DGR-039, DGR-042, DGR-043, DGR-052, DGR-053) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Release alpha only when V4 is correct and clears the pre-locked useful-speed requirement.
|
||||
|
||||
## Acceptance criteria
|
||||
|
||||
- [ ] Evaluate correctness, model fit, TTFT, prefill/decode speed, seam cost, memory, and failure rate against DGF-004 without changing thresholds.
|
||||
- [ ] Separate quant/model-fit gains from runtime/transport gains.
|
||||
- [ ] Decision is `alpha`, `optimize measured bottleneck`, or `stop`; failures cannot be relabeled as certification.
|
||||
- [ ] Alpha documentation states MTP is reserved but not implemented and identifies every dark hardware lane.
|
||||
- [ ] Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff.
|
||||
|
||||
## Shared quality gates
|
||||
|
||||
- Targeted deterministic tests pass; Python changes also pass `python -m compileall packages tests`.
|
||||
- `git diff --check` passes.
|
||||
- Default tests are model-download-free, API-credit-free, and GPU-free.
|
||||
- Evidence README records exact changed files, commands/results, limitations, and dependency handoff; no fabricated evidence or inherited completion credit.
|
||||
- Native changes pass focused out-of-tree CMake build and CTest; patch changes verify clean apply/check/reverse against the exact llama.cpp pin.
|
||||
- Runs are opt-in and record exact artifact/split hashes, runtime/upstream pin, backend/driver, hardware, network, commands, and raw metrics. Model artifacts use configured mounted-drive storage and never `/home`.
|
||||
- Preserve existing Transformers behavior and backend-agnostic Tracker routing/load balancing/billing/relay semantics unless an explicit versioned contract says otherwise. One scoped story commit is expected during execution, but this specification-materialization change is not committed.
|
||||
|
||||
## Evidence handoff
|
||||
|
||||
Write and verify `.scratch/distributed-gguf-runtime/evidence/DGR-054/README.md`. Until every criterion and applicable gate has real evidence, this story remains `passes: false`. Legacy evidence is provenance only, not completion credit.
|
||||
@@ -0,0 +1,39 @@
|
||||
<!-- GENERATED FROM prd.json — DO NOT EDIT AS AN INDEPENDENT SOURCE. prd.json IS AUTHORITATIVE. -->
|
||||
# DGR-055: Implement compatible continuous decode batching
|
||||
|
||||
- **Status / triage:** specification only; `ready-for-agent`; `passes: false`
|
||||
- **Execution mode:** `AFK`
|
||||
- **Milestone:** `M4`
|
||||
- **Dependencies:** `DGR-038`, `DGR-040`, `DGR-054`
|
||||
- **Blocks (derived):** `DGR-056`, `DGR-057`
|
||||
- **Labels:** `area:scheduler`, `area:batching`, `type:performance`, `priority:p1`, `ready-for-agent`
|
||||
- **Evidence class:** `fixture`
|
||||
- **Hardware:** `none`
|
||||
- **Model:** `generic`
|
||||
- **Upstream:** `no`
|
||||
|
||||
## Objective / description
|
||||
|
||||
Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`, source issue `.scratch/distributed-gguf-runtime/issues/055-implement-compatible-continuous-decode-batching.md`, and evidence READMEs for dependencies (DGR-038, DGR-040, DGR-054) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Batch compatible active sessions without violating route, recipe, position, or architecture state.
|
||||
|
||||
## Acceptance criteria
|
||||
|
||||
- [ ] Batch only sessions with compatible engine, recipe, phase, boundary schema, and state layout.
|
||||
- [ ] Preserve per-session positions, sequence IDs, outputs, cancellation, and accounting.
|
||||
- [ ] Decode receives bounded service while prefill remains schedulable.
|
||||
- [ ] Deterministic 1/2/4/8 concurrency tests show no cross-session corruption.
|
||||
- [ ] Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff.
|
||||
|
||||
## Shared quality gates
|
||||
|
||||
- Targeted deterministic tests pass; Python changes also pass `python -m compileall packages tests`.
|
||||
- `git diff --check` passes.
|
||||
- Default tests are model-download-free, API-credit-free, and GPU-free.
|
||||
- Evidence README records exact changed files, commands/results, limitations, and dependency handoff; no fabricated evidence or inherited completion credit.
|
||||
- Native changes pass focused out-of-tree CMake build and CTest; patch changes verify clean apply/check/reverse against the exact llama.cpp pin.
|
||||
- Runs are opt-in and record exact artifact/split hashes, runtime/upstream pin, backend/driver, hardware, network, commands, and raw metrics. Model artifacts use configured mounted-drive storage and never `/home`.
|
||||
- Preserve existing Transformers behavior and backend-agnostic Tracker routing/load balancing/billing/relay semantics unless an explicit versioned contract says otherwise. One scoped story commit is expected during execution, but this specification-materialization change is not committed.
|
||||
|
||||
## Evidence handoff
|
||||
|
||||
Write and verify `.scratch/distributed-gguf-runtime/evidence/DGR-055/README.md`. Until every criterion and applicable gate has real evidence, this story remains `passes: false`. Legacy evidence is provenance only, not completion credit.
|
||||
@@ -0,0 +1,39 @@
|
||||
<!-- GENERATED FROM prd.json — DO NOT EDIT AS AN INDEPENDENT SOURCE. prd.json IS AUTHORITATIVE. -->
|
||||
# DGR-056: Enforce bounded admission, queues, and backpressure
|
||||
|
||||
- **Status / triage:** specification only; `ready-for-agent`; `passes: false`
|
||||
- **Execution mode:** `AFK`
|
||||
- **Milestone:** `M4`
|
||||
- **Dependencies:** `DGR-055`
|
||||
- **Blocks (derived):** `DGR-057`, `DGR-058`, `DGR-060`
|
||||
- **Labels:** `area:scheduler`, `area:backpressure`, `type:performance`, `priority:p1`, `ready-for-agent`
|
||||
- **Evidence class:** `fixture`
|
||||
- **Hardware:** `none`
|
||||
- **Model:** `generic`
|
||||
- **Upstream:** `no`
|
||||
|
||||
## Objective / description
|
||||
|
||||
Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`, source issue `.scratch/distributed-gguf-runtime/issues/056-enforce-bounded-admission-queues-and-backpressure.md`, and evidence READMEs for dependencies (DGR-055) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Prevent weight, KV, state, scratch, and stream buffers from exceeding admitted capacity.
|
||||
|
||||
## Acceptance criteria
|
||||
|
||||
- [ ] Admission accounts separately for weights, KV/state, scratch, in-flight fragments, and queue slots.
|
||||
- [ ] Queue and stream limits produce structured retryable or terminal responses.
|
||||
- [ ] Prefill cannot starve decode and one route session cannot monopolize queue capacity.
|
||||
- [ ] Telemetry reports active sessions, queue depth/time, batch occupancy, memory pressure, and rejects.
|
||||
- [ ] Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff.
|
||||
|
||||
## Shared quality gates
|
||||
|
||||
- Targeted deterministic tests pass; Python changes also pass `python -m compileall packages tests`.
|
||||
- `git diff --check` passes.
|
||||
- Default tests are model-download-free, API-credit-free, and GPU-free.
|
||||
- Evidence README records exact changed files, commands/results, limitations, and dependency handoff; no fabricated evidence or inherited completion credit.
|
||||
- Native changes pass focused out-of-tree CMake build and CTest; patch changes verify clean apply/check/reverse against the exact llama.cpp pin.
|
||||
- Runs are opt-in and record exact artifact/split hashes, runtime/upstream pin, backend/driver, hardware, network, commands, and raw metrics. Model artifacts use configured mounted-drive storage and never `/home`.
|
||||
- Preserve existing Transformers behavior and backend-agnostic Tracker routing/load balancing/billing/relay semantics unless an explicit versioned contract says otherwise. One scoped story commit is expected during execution, but this specification-materialization change is not committed.
|
||||
|
||||
## Evidence handoff
|
||||
|
||||
Write and verify `.scratch/distributed-gguf-runtime/evidence/DGR-056/README.md`. Until every criterion and applicable gate has real evidence, this story remains `passes: false`. Legacy evidence is provenance only, not completion credit.
|
||||
@@ -0,0 +1,39 @@
|
||||
<!-- GENERATED FROM prd.json — DO NOT EDIT AS AN INDEPENDENT SOURCE. prd.json IS AUTHORITATIVE. -->
|
||||
# DGR-057: Benchmark batching saturation and fairness
|
||||
|
||||
- **Status / triage:** specification only; `ready-for-agent`; `passes: false`
|
||||
- **Execution mode:** `AFK`
|
||||
- **Milestone:** `M4`
|
||||
- **Dependencies:** `DGR-055`, `DGR-056`
|
||||
- **Blocks (derived):** `DGR-061`, `DGR-063`, `DGR-070`
|
||||
- **Labels:** `area:performance`, `area:batching`, `type:benchmark`, `priority:p1`, `ready-for-agent`
|
||||
- **Evidence class:** `real-hardware`
|
||||
- **Hardware:** `required`
|
||||
- **Model:** `dense-llama+deepseek-v4`
|
||||
- **Upstream:** `no`
|
||||
|
||||
## Objective / description
|
||||
|
||||
Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`, source issue `.scratch/distributed-gguf-runtime/issues/057-benchmark-batching-saturation-and-fairness.md`, and evidence READMEs for dependencies (DGR-055, DGR-056) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Identify useful concurrency and saturation points without assuming one global batch size.
|
||||
|
||||
## Acceptance criteria
|
||||
|
||||
- [ ] Run controlled concurrency 1/2/4/8 and record aggregate throughput, per-request p50/p95, TTFT, queue time, occupancy, and memory.
|
||||
- [ ] Measure dense and V4 lanes separately where hardware permits.
|
||||
- [ ] Verify bounded fairness and no prefill/decode starvation.
|
||||
- [ ] Produce machine-readable saturation recommendations consumed by capability reporting, not hardcoded constants.
|
||||
- [ ] Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff.
|
||||
|
||||
## Shared quality gates
|
||||
|
||||
- Targeted deterministic tests pass; Python changes also pass `python -m compileall packages tests`.
|
||||
- `git diff --check` passes.
|
||||
- Default tests are model-download-free, API-credit-free, and GPU-free.
|
||||
- Evidence README records exact changed files, commands/results, limitations, and dependency handoff; no fabricated evidence or inherited completion credit.
|
||||
- Native changes pass focused out-of-tree CMake build and CTest; patch changes verify clean apply/check/reverse against the exact llama.cpp pin.
|
||||
- Runs are opt-in and record exact artifact/split hashes, runtime/upstream pin, backend/driver, hardware, network, commands, and raw metrics. Model artifacts use configured mounted-drive storage and never `/home`.
|
||||
- Preserve existing Transformers behavior and backend-agnostic Tracker routing/load balancing/billing/relay semantics unless an explicit versioned contract says otherwise. One scoped story commit is expected during execution, but this specification-materialization change is not committed.
|
||||
|
||||
## Evidence handoff
|
||||
|
||||
Write and verify `.scratch/distributed-gguf-runtime/evidence/DGR-057/README.md`. Until every criterion and applicable gate has real evidence, this story remains `passes: false`. Legacy evidence is provenance only, not completion credit.
|
||||
@@ -0,0 +1,39 @@
|
||||
<!-- GENERATED FROM prd.json — DO NOT EDIT AS AN INDEPENDENT SOURCE. prd.json IS AUTHORITATIVE. -->
|
||||
# DGR-058: Harden worker and stream failure semantics
|
||||
|
||||
- **Status / triage:** specification only; `ready-for-agent`; `passes: false`
|
||||
- **Execution mode:** `AFK`
|
||||
- **Milestone:** `M4`
|
||||
- **Dependencies:** `DGR-040`, `DGR-042`, `DGR-056`
|
||||
- **Blocks (derived):** `DGR-059`, `DGR-060`, `DGR-061`
|
||||
- **Labels:** `area:reliability`, `area:failure`, `type:hardening`, `priority:p1`, `ready-for-agent`
|
||||
- **Evidence class:** `fixture`
|
||||
- **Hardware:** `none`
|
||||
- **Model:** `generic`
|
||||
- **Upstream:** `no`
|
||||
|
||||
## Objective / description
|
||||
|
||||
Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`, source issue `.scratch/distributed-gguf-runtime/issues/058-harden-worker-and-stream-failure-semantics.md`, and evidence READMEs for dependencies (DGR-040, DGR-042, DGR-056) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Ensure malformed input, process death, transport reset, and cancellation terminate cleanly.
|
||||
|
||||
## Acceptance criteria
|
||||
|
||||
- [ ] Test worker death, stream reset, malformed bundle, checksum failure, deadline, cache miss, stale epoch, and partial fragment loss.
|
||||
- [ ] Cancellation propagates across all stages and releases KV/state, queue entries, and fragment buffers.
|
||||
- [ ] Duplicate steps are idempotent; uncertain mutations are never silently replayed.
|
||||
- [ ] Billing/work outcomes distinguish completed, cancelled, failed, and unverified work.
|
||||
- [ ] Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff.
|
||||
|
||||
## Shared quality gates
|
||||
|
||||
- Targeted deterministic tests pass; Python changes also pass `python -m compileall packages tests`.
|
||||
- `git diff --check` passes.
|
||||
- Default tests are model-download-free, API-credit-free, and GPU-free.
|
||||
- Evidence README records exact changed files, commands/results, limitations, and dependency handoff; no fabricated evidence or inherited completion credit.
|
||||
- Native changes pass focused out-of-tree CMake build and CTest; patch changes verify clean apply/check/reverse against the exact llama.cpp pin.
|
||||
- Runs are opt-in and record exact artifact/split hashes, runtime/upstream pin, backend/driver, hardware, network, commands, and raw metrics. Model artifacts use configured mounted-drive storage and never `/home`.
|
||||
- Preserve existing Transformers behavior and backend-agnostic Tracker routing/load balancing/billing/relay semantics unless an explicit versioned contract says otherwise. One scoped story commit is expected during execution, but this specification-materialization change is not committed.
|
||||
|
||||
## Evidence handoff
|
||||
|
||||
Write and verify `.scratch/distributed-gguf-runtime/evidence/DGR-058/README.md`. Until every criterion and applicable gate has real evidence, this story remains `passes: false`. Legacy evidence is provenance only, not completion credit.
|
||||
@@ -0,0 +1,39 @@
|
||||
<!-- GENERATED FROM prd.json — DO NOT EDIT AS AN INDEPENDENT SOURCE. prd.json IS AUTHORITATIVE. -->
|
||||
# DGR-059: Implement alpha-safe route recovery
|
||||
|
||||
- **Status / triage:** specification only; `ready-for-agent`; `passes: false`
|
||||
- **Execution mode:** `AFK`
|
||||
- **Milestone:** `M4`
|
||||
- **Dependencies:** `DGR-043`, `DGR-058`
|
||||
- **Blocks (derived):** `DGR-070`
|
||||
- **Labels:** `area:recovery`, `area:routing`, `type:hardening`, `priority:p1`, `ready-for-agent`
|
||||
- **Evidence class:** `fixture`
|
||||
- **Hardware:** `none`
|
||||
- **Model:** `generic`
|
||||
- **Upstream:** `no`
|
||||
|
||||
## Objective / description
|
||||
|
||||
Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`, source issue `.scratch/distributed-gguf-runtime/issues/059-implement-alpha-safe-route-recovery.md`, and evidence READMEs for dependencies (DGR-043, DGR-058) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Recover from route loss without importing or continuing unverified state.
|
||||
|
||||
## Acceptance criteria
|
||||
|
||||
- [ ] On route loss or local-state cache miss, restart from token zero or re-prefill on a newly compatible route according to the locked alpha contract.
|
||||
- [ ] Never import KV, CSA, HCA, SWA, indexer, compressor, recurrent, or MTP cache/state across workers.
|
||||
- [ ] Keep exact same-route duplicate delivery idempotent while cross-route continuation fails closed.
|
||||
- [ ] Test direct/relay loss, cache miss, replacement selection, client cancellation, and billing reconciliation.
|
||||
- [ ] Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff.
|
||||
|
||||
## Shared quality gates
|
||||
|
||||
- Targeted deterministic tests pass; Python changes also pass `python -m compileall packages tests`.
|
||||
- `git diff --check` passes.
|
||||
- Default tests are model-download-free, API-credit-free, and GPU-free.
|
||||
- Evidence README records exact changed files, commands/results, limitations, and dependency handoff; no fabricated evidence or inherited completion credit.
|
||||
- Native changes pass focused out-of-tree CMake build and CTest; patch changes verify clean apply/check/reverse against the exact llama.cpp pin.
|
||||
- Runs are opt-in and record exact artifact/split hashes, runtime/upstream pin, backend/driver, hardware, network, commands, and raw metrics. Model artifacts use configured mounted-drive storage and never `/home`.
|
||||
- Preserve existing Transformers behavior and backend-agnostic Tracker routing/load balancing/billing/relay semantics unless an explicit versioned contract says otherwise. One scoped story commit is expected during execution, but this specification-materialization change is not committed.
|
||||
|
||||
## Evidence handoff
|
||||
|
||||
Write and verify `.scratch/distributed-gguf-runtime/evidence/DGR-059/README.md`. Until every criterion and applicable gate has real evidence, this story remains `passes: false`. Legacy evidence is provenance only, not completion credit.
|
||||
@@ -0,0 +1,39 @@
|
||||
<!-- GENERATED FROM prd.json — DO NOT EDIT AS AN INDEPENDENT SOURCE. prd.json IS AUTHORITATIVE. -->
|
||||
# DGR-060: Certify V4 long-context state correctness
|
||||
|
||||
- **Status / triage:** specification only; `ready-for-agent`; `passes: false`
|
||||
- **Execution mode:** `AFK`
|
||||
- **Milestone:** `M4`
|
||||
- **Dependencies:** `DGR-051`, `DGR-056`, `DGR-058`
|
||||
- **Blocks (derived):** `DGR-062`, `DGR-064`, `DGR-065`, `DGR-066`, `DGR-070`
|
||||
- **Labels:** `area:deepseek-v4`, `area:long-context`, `type:certification`, `priority:p1`, `ready-for-agent`
|
||||
- **Evidence class:** `real-hardware`
|
||||
- **Hardware:** `required`
|
||||
- **Model:** `deepseek-v4-flash`
|
||||
- **Upstream:** `yes`
|
||||
|
||||
## Objective / description
|
||||
|
||||
Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`, source issue `.scratch/distributed-gguf-runtime/issues/060-certify-v4-long-context-state-correctness.md`, and evidence READMEs for dependencies (DGR-051, DGR-056, DGR-058) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Prove V4’s KV and auxiliary state remain correct and bounded at long contexts.
|
||||
|
||||
## Acceptance criteria
|
||||
|
||||
- [ ] Exercise pre-locked context lengths covering multiple prefill chunks and sustained decode.
|
||||
- [ ] Validate KV plus CSA/HCA/SWA/indexer/compressor state positions across every stage.
|
||||
- [ ] Measure memory growth, fragment sizes, TTFT, decode degradation, cancellation latency, and cleanup.
|
||||
- [ ] Cache mismatch, truncation, and context-limit behavior fail deterministically.
|
||||
- [ ] Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff.
|
||||
|
||||
## Shared quality gates
|
||||
|
||||
- Targeted deterministic tests pass; Python changes also pass `python -m compileall packages tests`.
|
||||
- `git diff --check` passes.
|
||||
- Default tests are model-download-free, API-credit-free, and GPU-free.
|
||||
- Evidence README records exact changed files, commands/results, limitations, and dependency handoff; no fabricated evidence or inherited completion credit.
|
||||
- Native changes pass focused out-of-tree CMake build and CTest; patch changes verify clean apply/check/reverse against the exact llama.cpp pin.
|
||||
- Runs are opt-in and record exact artifact/split hashes, runtime/upstream pin, backend/driver, hardware, network, commands, and raw metrics. Model artifacts use configured mounted-drive storage and never `/home`.
|
||||
- Preserve existing Transformers behavior and backend-agnostic Tracker routing/load balancing/billing/relay semantics unless an explicit versioned contract says otherwise. One scoped story commit is expected during execution, but this specification-materialization change is not committed.
|
||||
|
||||
## Evidence handoff
|
||||
|
||||
Write and verify `.scratch/distributed-gguf-runtime/evidence/DGR-060/README.md`. Until every criterion and applicable gate has real evidence, this story remains `passes: false`. Legacy evidence is provenance only, not completion credit.
|
||||
@@ -0,0 +1,39 @@
|
||||
<!-- GENERATED FROM prd.json — DO NOT EDIT AS AN INDEPENDENT SOURCE. prd.json IS AUTHORITATIVE. -->
|
||||
# DGR-061: Certify existing routing with 10+ GGUF stage candidates
|
||||
|
||||
- **Status / triage:** specification only; `ready-for-agent`; `passes: false`
|
||||
- **Execution mode:** `AFK`
|
||||
- **Milestone:** `M4`
|
||||
- **Dependencies:** `DGR-043`, `DGR-057`, `DGR-058`
|
||||
- **Blocks (derived):** `DGR-062`, `DGR-063`
|
||||
- **Labels:** `area:tracker`, `area:scale`, `type:simulation`, `priority:p1`, `ready-for-agent`
|
||||
- **Evidence class:** `fixture`
|
||||
- **Hardware:** `none`
|
||||
- **Model:** `generic`
|
||||
- **Upstream:** `no`
|
||||
|
||||
## Objective / description
|
||||
|
||||
Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`, source issue `.scratch/distributed-gguf-runtime/issues/061-certify-existing-routing-with-10-gguf-stage-candidates.md`, and evidence READMEs for dependencies (DGR-043, DGR-057, DGR-058) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Certify that existing backend-agnostic routing consumes GGUF compatibility and measured-cost inputs for a 10+ candidate scenario without algorithm or policy redesign.
|
||||
|
||||
## Acceptance criteria
|
||||
|
||||
- [ ] Generate deterministic pools with 10+ compatible GGUF stage candidates plus slower, overloaded, unhealthy, and incompatible alternatives.
|
||||
- [ ] Run the existing routing implementation unchanged and verify complete coverage, compatibility, acyclicity, and use of measured inputs.
|
||||
- [ ] Regression-test that no stage count, quant, fixed split, architecture, or backend sequence is encoded in production routing policy.
|
||||
- [ ] Verify existing route recomputation reacts to measured load/failure while tracker, load-balancing, billing, relay, and provider semantics remain unchanged.
|
||||
- [ ] Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff.
|
||||
|
||||
## Shared quality gates
|
||||
|
||||
- Targeted deterministic tests pass; Python changes also pass `python -m compileall packages tests`.
|
||||
- `git diff --check` passes.
|
||||
- Default tests are model-download-free, API-credit-free, and GPU-free.
|
||||
- Evidence README records exact changed files, commands/results, limitations, and dependency handoff; no fabricated evidence or inherited completion credit.
|
||||
- Native changes pass focused out-of-tree CMake build and CTest; patch changes verify clean apply/check/reverse against the exact llama.cpp pin.
|
||||
- Runs are opt-in and record exact artifact/split hashes, runtime/upstream pin, backend/driver, hardware, network, commands, and raw metrics. Model artifacts use configured mounted-drive storage and never `/home`.
|
||||
- Preserve existing Transformers behavior and backend-agnostic Tracker routing/load balancing/billing/relay semantics unless an explicit versioned contract says otherwise. One scoped story commit is expected during execution, but this specification-materialization change is not committed.
|
||||
|
||||
## Evidence handoff
|
||||
|
||||
Write and verify `.scratch/distributed-gguf-runtime/evidence/DGR-061/README.md`. Until every criterion and applicable gate has real evidence, this story remains `passes: false`. Legacy evidence is provenance only, not completion credit.
|
||||
@@ -0,0 +1,40 @@
|
||||
<!-- GENERATED FROM prd.json — DO NOT EDIT AS AN INDEPENDENT SOURCE. prd.json IS AUTHORITATIVE. -->
|
||||
# DGR-062: Certify a dynamic real 10+ stage V4 scenario
|
||||
|
||||
- **Status / triage:** specification only; `ready-for-human`; `passes: false`
|
||||
- **Execution mode:** `HITL`
|
||||
- **Milestone:** `M4`
|
||||
- **Dependencies:** `DGR-053`, `DGR-060`, `DGR-061`
|
||||
- **Blocks (derived):** `DGR-067`, `DGR-070`
|
||||
- **Labels:** `area:deepseek-v4`, `area:scale`, `area:hardware`, `type:certification`, `priority:p1`, `gate:hitl`, `ready-for-human`
|
||||
- **Evidence class:** `real-hardware`
|
||||
- **Hardware:** `required`
|
||||
- **Model:** `deepseek-v4-flash`
|
||||
- **Upstream:** `yes`
|
||||
|
||||
## Objective / description
|
||||
|
||||
Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`, source issue `.scratch/distributed-gguf-runtime/issues/062-certify-a-dynamic-real-10-stage-v4-scenario.md`, and evidence READMEs for dependencies (DGR-053, DGR-060, DGR-061) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Demonstrate that a large real route can be dynamically selected and usefully execute V4.
|
||||
|
||||
## Acceptance criteria
|
||||
|
||||
- [ ] Run one real 10+-stage V4 certification scenario; stage count, quant, and split remain scenario metadata only.
|
||||
- [ ] Every selected stage proves real work, exact compatible identity, local state ownership, and bounded resources.
|
||||
- [ ] Record end-to-end and per-stage TTFT, prefill/decode, seam cost, queueing, memory, failures, and cleanup.
|
||||
- [ ] Inject at least one incompatible or degraded candidate and verify dynamic exclusion/reselection.
|
||||
- [ ] The scenario must meet its pre-locked usefulness threshold or remain failed evidence.
|
||||
- [ ] Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff.
|
||||
|
||||
## Shared quality gates
|
||||
|
||||
- Targeted deterministic tests pass; Python changes also pass `python -m compileall packages tests`.
|
||||
- `git diff --check` passes.
|
||||
- Default tests are model-download-free, API-credit-free, and GPU-free.
|
||||
- Evidence README records exact changed files, commands/results, limitations, and dependency handoff; no fabricated evidence or inherited completion credit.
|
||||
- Native changes pass focused out-of-tree CMake build and CTest; patch changes verify clean apply/check/reverse against the exact llama.cpp pin.
|
||||
- Runs are opt-in and record exact artifact/split hashes, runtime/upstream pin, backend/driver, hardware, network, commands, and raw metrics. Model artifacts use configured mounted-drive storage and never `/home`.
|
||||
- Preserve existing Transformers behavior and backend-agnostic Tracker routing/load balancing/billing/relay semantics unless an explicit versioned contract says otherwise. One scoped story commit is expected during execution, but this specification-materialization change is not committed.
|
||||
|
||||
## Evidence handoff
|
||||
|
||||
Write and verify `.scratch/distributed-gguf-runtime/evidence/DGR-062/README.md`. Until every criterion and applicable gate has real evidence, this story remains `passes: false`. Legacy evidence is provenance only, not completion credit.
|
||||
@@ -0,0 +1,39 @@
|
||||
<!-- GENERATED FROM prd.json — DO NOT EDIT AS AN INDEPENDENT SOURCE. prd.json IS AUTHORITATIVE. -->
|
||||
# DGR-063: Profile and optimize the critical seam
|
||||
|
||||
- **Status / triage:** specification only; `ready-for-agent`; `passes: false`
|
||||
- **Execution mode:** `AFK`
|
||||
- **Milestone:** `M4`
|
||||
- **Dependencies:** `DGR-057`, `DGR-061`
|
||||
- **Blocks (derived):** `DGR-064`
|
||||
- **Labels:** `area:performance`, `type:optimization`, `priority:p1`, `ready-for-agent`
|
||||
- **Evidence class:** `real-hardware`
|
||||
- **Hardware:** `required`
|
||||
- **Model:** `generic`
|
||||
- **Upstream:** `conditional`
|
||||
|
||||
## Objective / description
|
||||
|
||||
Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`, source issue `.scratch/distributed-gguf-runtime/issues/063-profile-and-optimize-the-critical-seam.md`, and evidence READMEs for dependencies (DGR-057, DGR-061) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Optimize only the measured dominant compute, serialization, copy, or transport bottleneck.
|
||||
|
||||
## Acceptance criteria
|
||||
|
||||
- [ ] Profile worker compute, tensor conversion, copies, protobuf framing, compression, relay/direct transport, queueing, and synchronization.
|
||||
- [ ] Select one dominant bottleneck from evidence and lock its before/after benchmark.
|
||||
- [ ] Implement one bounded optimization without weakening correctness or protocol identity.
|
||||
- [ ] Report whether the optimization changes TTFT, prefill, decode, throughput, or memory and preserve raw data.
|
||||
- [ ] Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff.
|
||||
|
||||
## Shared quality gates
|
||||
|
||||
- Targeted deterministic tests pass; Python changes also pass `python -m compileall packages tests`.
|
||||
- `git diff --check` passes.
|
||||
- Default tests are model-download-free, API-credit-free, and GPU-free.
|
||||
- Evidence README records exact changed files, commands/results, limitations, and dependency handoff; no fabricated evidence or inherited completion credit.
|
||||
- Native changes pass focused out-of-tree CMake build and CTest; patch changes verify clean apply/check/reverse against the exact llama.cpp pin.
|
||||
- Runs are opt-in and record exact artifact/split hashes, runtime/upstream pin, backend/driver, hardware, network, commands, and raw metrics. Model artifacts use configured mounted-drive storage and never `/home`.
|
||||
- Preserve existing Transformers behavior and backend-agnostic Tracker routing/load balancing/billing/relay semantics unless an explicit versioned contract says otherwise. One scoped story commit is expected during execution, but this specification-materialization change is not committed.
|
||||
|
||||
## Evidence handoff
|
||||
|
||||
Write and verify `.scratch/distributed-gguf-runtime/evidence/DGR-063/README.md`. Until every criterion and applicable gate has real evidence, this story remains `passes: false`. Legacy evidence is provenance only, not completion credit.
|
||||
@@ -0,0 +1,39 @@
|
||||
<!-- GENERATED FROM prd.json — DO NOT EDIT AS AN INDEPENDENT SOURCE. prd.json IS AUTHORITATIVE. -->
|
||||
# DGR-064: Add negotiated activation compression
|
||||
|
||||
- **Status / triage:** specification only; `ready-for-agent`; `passes: false`
|
||||
- **Execution mode:** `AFK`
|
||||
- **Milestone:** `M4`
|
||||
- **Dependencies:** `DGR-060`, `DGR-063`
|
||||
- **Blocks (derived):** `DGR-066`, `DGR-070`
|
||||
- **Labels:** `area:protocol`, `area:compression`, `type:optimization`, `priority:p1`, `ready-for-agent`
|
||||
- **Evidence class:** `real-hardware`
|
||||
- **Hardware:** `required`
|
||||
- **Model:** `deepseek-v4-flash`
|
||||
- **Upstream:** `no`
|
||||
|
||||
## Objective / description
|
||||
|
||||
Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`, source issue `.scratch/distributed-gguf-runtime/issues/064-add-negotiated-activation-compression.md`, and evidence READMEs for dependencies (DGR-060, DGR-063) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Reduce V4 seam cost only when a certified compression recipe improves end-to-end performance acceptably.
|
||||
|
||||
## Acceptance criteria
|
||||
|
||||
- [ ] Negotiate compression through recipe identity; unnegotiated or mismatched compression fails closed.
|
||||
- [ ] Preserve names, shapes, semantic axes, token-ID sideband, and checksums.
|
||||
- [ ] Measure quality drift, encode/decode cost, bytes, TTFT, and throughput against uncompressed boundaries.
|
||||
- [ ] Compression remains dark unless it meets pre-locked quality and speed thresholds.
|
||||
- [ ] Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff.
|
||||
|
||||
## Shared quality gates
|
||||
|
||||
- Targeted deterministic tests pass; Python changes also pass `python -m compileall packages tests`.
|
||||
- `git diff --check` passes.
|
||||
- Default tests are model-download-free, API-credit-free, and GPU-free.
|
||||
- Evidence README records exact changed files, commands/results, limitations, and dependency handoff; no fabricated evidence or inherited completion credit.
|
||||
- Native changes pass focused out-of-tree CMake build and CTest; patch changes verify clean apply/check/reverse against the exact llama.cpp pin.
|
||||
- Runs are opt-in and record exact artifact/split hashes, runtime/upstream pin, backend/driver, hardware, network, commands, and raw metrics. Model artifacts use configured mounted-drive storage and never `/home`.
|
||||
- Preserve existing Transformers behavior and backend-agnostic Tracker routing/load balancing/billing/relay semantics unless an explicit versioned contract says otherwise. One scoped story commit is expected during execution, but this specification-materialization change is not committed.
|
||||
|
||||
## Evidence handoff
|
||||
|
||||
Write and verify `.scratch/distributed-gguf-runtime/evidence/DGR-064/README.md`. Until every criterion and applicable gate has real evidence, this story remains `passes: false`. Legacy evidence is provenance only, not completion credit.
|
||||
@@ -0,0 +1,39 @@
|
||||
<!-- GENERATED FROM prd.json — DO NOT EDIT AS AN INDEPENDENT SOURCE. prd.json IS AUTHORITATIVE. -->
|
||||
# DGR-065: Define V4 MTP ownership and distributed state contract
|
||||
|
||||
- **Status / triage:** specification only; `ready-for-agent`; `passes: false`
|
||||
- **Execution mode:** `AFK`
|
||||
- **Milestone:** `M4`
|
||||
- **Dependencies:** `DGR-051`, `DGR-054`, `DGR-060`
|
||||
- **Blocks (derived):** `DGR-066`
|
||||
- **Labels:** `area:deepseek-v4`, `area:mtp`, `type:contract`, `priority:p1`, `ready-for-agent`
|
||||
- **Evidence class:** `fixture`
|
||||
- **Hardware:** `none`
|
||||
- **Model:** `deepseek-v4-flash`
|
||||
- **Upstream:** `yes`
|
||||
|
||||
## Objective / description
|
||||
|
||||
Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`, source issue `.scratch/distributed-gguf-runtime/issues/065-define-v4-mtp-ownership-and-distributed-state-contract.md`, and evidence READMEs for dependencies (DGR-051, DGR-054, DGR-060) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Lock MTP tensor, execution, boundary, acceptance/rejection, and session-state ownership before implementation while keeping MTP disabled for alpha.
|
||||
|
||||
## Acceptance criteria
|
||||
|
||||
- [ ] Derive exact MTP tensor and execution ownership from the pinned V4 target and upstream llama.cpp graph, distinguishing main-layer, tail, and MTP responsibilities.
|
||||
- [ ] Define typed MTP inputs/outputs plus accepted-token, rejection, rollback/truncation, position, cache, and session/epoch lifecycle semantics.
|
||||
- [ ] Specify which MTP state remains shard-local and which typed boundary values cross a seam; prohibit WAN migration of KV or V4 auxiliary caches.
|
||||
- [ ] Keep every MTP recipe disabled and unroutable for alpha, with fail-closed capability negotiation and deterministic contract fixtures.
|
||||
- [ ] Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff.
|
||||
|
||||
## Shared quality gates
|
||||
|
||||
- Targeted deterministic tests pass; Python changes also pass `python -m compileall packages tests`.
|
||||
- `git diff --check` passes.
|
||||
- Default tests are model-download-free, API-credit-free, and GPU-free.
|
||||
- Evidence README records exact changed files, commands/results, limitations, and dependency handoff; no fabricated evidence or inherited completion credit.
|
||||
- Native changes pass focused out-of-tree CMake build and CTest; patch changes verify clean apply/check/reverse against the exact llama.cpp pin.
|
||||
- Runs are opt-in and record exact artifact/split hashes, runtime/upstream pin, backend/driver, hardware, network, commands, and raw metrics. Model artifacts use configured mounted-drive storage and never `/home`.
|
||||
- Preserve existing Transformers behavior and backend-agnostic Tracker routing/load balancing/billing/relay semantics unless an explicit versioned contract says otherwise. One scoped story commit is expected during execution, but this specification-materialization change is not committed.
|
||||
|
||||
## Evidence handoff
|
||||
|
||||
Write and verify `.scratch/distributed-gguf-runtime/evidence/DGR-065/README.md`. Until every criterion and applicable gate has real evidence, this story remains `passes: false`. Legacy evidence is provenance only, not completion credit.
|
||||
@@ -0,0 +1,39 @@
|
||||
<!-- GENERATED FROM prd.json — DO NOT EDIT AS AN INDEPENDENT SOURCE. prd.json IS AUTHORITATIVE. -->
|
||||
# DGR-066: Implement and benchmark V4 MTP
|
||||
|
||||
- **Status / triage:** specification only; `ready-for-agent`; `passes: false`
|
||||
- **Execution mode:** `AFK`
|
||||
- **Milestone:** `M4`
|
||||
- **Dependencies:** `DGR-054`, `DGR-060`, `DGR-064`, `DGR-065`
|
||||
- **Blocks (derived):** `DGR-067`, `DGR-070`
|
||||
- **Labels:** `area:deepseek-v4`, `area:mtp`, `type:runtime`, `priority:p1`, `ready-for-agent`
|
||||
- **Evidence class:** `real-hardware`
|
||||
- **Hardware:** `required`
|
||||
- **Model:** `deepseek-v4-flash`
|
||||
- **Upstream:** `yes`
|
||||
|
||||
## Objective / description
|
||||
|
||||
Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`, source issue `.scratch/distributed-gguf-runtime/issues/066-implement-and-benchmark-v4-mtp.md`, and evidence READMEs for dependencies (DGR-054, DGR-060, DGR-064, DGR-065) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Implement the locked MTP contract around upstream llama.cpp before beta, without making MTP an alpha prerequisite.
|
||||
|
||||
## Acceptance criteria
|
||||
|
||||
- [ ] Implement the exact DGR-065 MTP ownership and typed state contract against the pinned upstream V4 graph while preserving shard-local caches.
|
||||
- [ ] Pass whole-model versus ranged MTP correctness, accepted-token, rejection, rollback/truncation, and session-isolation tests.
|
||||
- [ ] Benchmark MTP-off versus MTP-on quality, accepted-token rate, TTFT, decode speed, seam bytes, and memory on the locked lane.
|
||||
- [ ] Distinguish implemented, certified, disabled, and unsupported MTP recipes in fail-closed capability advertisement.
|
||||
- [ ] Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff.
|
||||
|
||||
## Shared quality gates
|
||||
|
||||
- Targeted deterministic tests pass; Python changes also pass `python -m compileall packages tests`.
|
||||
- `git diff --check` passes.
|
||||
- Default tests are model-download-free, API-credit-free, and GPU-free.
|
||||
- Evidence README records exact changed files, commands/results, limitations, and dependency handoff; no fabricated evidence or inherited completion credit.
|
||||
- Native changes pass focused out-of-tree CMake build and CTest; patch changes verify clean apply/check/reverse against the exact llama.cpp pin.
|
||||
- Runs are opt-in and record exact artifact/split hashes, runtime/upstream pin, backend/driver, hardware, network, commands, and raw metrics. Model artifacts use configured mounted-drive storage and never `/home`.
|
||||
- Preserve existing Transformers behavior and backend-agnostic Tracker routing/load balancing/billing/relay semantics unless an explicit versioned contract says otherwise. One scoped story commit is expected during execution, but this specification-materialization change is not committed.
|
||||
|
||||
## Evidence handoff
|
||||
|
||||
Write and verify `.scratch/distributed-gguf-runtime/evidence/DGR-066/README.md`. Until every criterion and applicable gate has real evidence, this story remains `passes: false`. Legacy evidence is provenance only, not completion credit.
|
||||
@@ -0,0 +1,40 @@
|
||||
<!-- GENERATED FROM prd.json — DO NOT EDIT AS AN INDEPENDENT SOURCE. prd.json IS AUTHORITATIVE. -->
|
||||
# DGR-067: Certify the backend capability matrix
|
||||
|
||||
- **Status / triage:** specification only; `ready-for-human`; `passes: false`
|
||||
- **Execution mode:** `HITL`
|
||||
- **Milestone:** `M4`
|
||||
- **Dependencies:** `DGR-030`, `DGR-053`, `DGR-062`, `DGR-066`
|
||||
- **Blocks (derived):** `DGR-068`, `DGR-070`
|
||||
- **Labels:** `area:hardware`, `area:admission`, `type:certification`, `priority:p1`, `gate:hitl`, `ready-for-human`
|
||||
- **Evidence class:** `real-hardware`
|
||||
- **Hardware:** `required`
|
||||
- **Model:** `deepseek-v4-flash`
|
||||
- **Upstream:** `yes`
|
||||
|
||||
## Objective / description
|
||||
|
||||
Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`, source issue `.scratch/distributed-gguf-runtime/issues/067-certify-the-backend-capability-matrix.md`, and evidence READMEs for dependencies (DGR-030, DGR-053, DGR-062, DGR-066) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Publish only backend/model/recipe lanes proven on actual CPU, CUDA, ROCm, Vulkan, or Metal hardware.
|
||||
|
||||
## Acceptance criteria
|
||||
|
||||
- [ ] Maintain independent build and certification status for CPU, CUDA, ROCm, Vulkan, and Metal.
|
||||
- [ ] Each advertised lane includes real hardware/driver/runtime/model evidence for parity, concurrency, cancellation, cleanup, and useful speed.
|
||||
- [ ] Build success alone never makes a lane routable; unavailable hardware remains explicitly dark.
|
||||
- [ ] Tracker admission consumes signed/versioned certification records rather than backend-name allowlists.
|
||||
- [ ] Mixed-backend routes require exact compatibility evidence and fail closed otherwise.
|
||||
- [ ] Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff.
|
||||
|
||||
## Shared quality gates
|
||||
|
||||
- Targeted deterministic tests pass; Python changes also pass `python -m compileall packages tests`.
|
||||
- `git diff --check` passes.
|
||||
- Default tests are model-download-free, API-credit-free, and GPU-free.
|
||||
- Evidence README records exact changed files, commands/results, limitations, and dependency handoff; no fabricated evidence or inherited completion credit.
|
||||
- Native changes pass focused out-of-tree CMake build and CTest; patch changes verify clean apply/check/reverse against the exact llama.cpp pin.
|
||||
- Runs are opt-in and record exact artifact/split hashes, runtime/upstream pin, backend/driver, hardware, network, commands, and raw metrics. Model artifacts use configured mounted-drive storage and never `/home`.
|
||||
- Preserve existing Transformers behavior and backend-agnostic Tracker routing/load balancing/billing/relay semantics unless an explicit versioned contract says otherwise. One scoped story commit is expected during execution, but this specification-materialization change is not committed.
|
||||
|
||||
## Evidence handoff
|
||||
|
||||
Write and verify `.scratch/distributed-gguf-runtime/evidence/DGR-067/README.md`. Until every criterion and applicable gate has real evidence, this story remains `passes: false`. Legacy evidence is provenance only, not completion credit.
|
||||
@@ -0,0 +1,39 @@
|
||||
<!-- GENERATED FROM prd.json — DO NOT EDIT AS AN INDEPENDENT SOURCE. prd.json IS AUTHORITATIVE. -->
|
||||
# DGR-068: Package reproducible native worker releases
|
||||
|
||||
- **Status / triage:** specification only; `ready-for-agent`; `passes: false`
|
||||
- **Execution mode:** `AFK`
|
||||
- **Milestone:** `M5`
|
||||
- **Dependencies:** `DGR-030`, `DGR-054`, `DGR-067`
|
||||
- **Blocks (derived):** `DGR-070`
|
||||
- **Labels:** `area:packaging`, `area:release`, `type:delivery`, `priority:p1`, `ready-for-agent`
|
||||
- **Evidence class:** `release`
|
||||
- **Hardware:** `optional`
|
||||
- **Model:** `generic`
|
||||
- **Upstream:** `yes`
|
||||
|
||||
## Objective / description
|
||||
|
||||
Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`, source issue `.scratch/distributed-gguf-runtime/issues/068-package-reproducible-native-worker-releases.md`, and evidence READMEs for dependencies (DGR-030, DGR-054, DGR-067) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Produce installable worker packages that preserve exact source, patch, protocol, and certification identity.
|
||||
|
||||
## Acceptance criteria
|
||||
|
||||
- [ ] Package worker binaries/configuration for supported host/backend combinations without bundling an unverified llama.cpp tree.
|
||||
- [ ] Embed protocol, engine, upstream pin, patch-stack, build-toolchain, and certification fingerprints.
|
||||
- [ ] Installation/startup refuses mismatched artifacts, runtime recipes, or unsupported hardware lanes.
|
||||
- [ ] Produce checksums, SBOM/license attribution, reproducible build instructions, and smoke tests.
|
||||
- [ ] Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff.
|
||||
|
||||
## Shared quality gates
|
||||
|
||||
- Targeted deterministic tests pass; Python changes also pass `python -m compileall packages tests`.
|
||||
- `git diff --check` passes.
|
||||
- Default tests are model-download-free, API-credit-free, and GPU-free.
|
||||
- Evidence README records exact changed files, commands/results, limitations, and dependency handoff; no fabricated evidence or inherited completion credit.
|
||||
- Native changes pass focused out-of-tree CMake build and CTest; patch changes verify clean apply/check/reverse against the exact llama.cpp pin.
|
||||
- Runs are opt-in and record exact artifact/split hashes, runtime/upstream pin, backend/driver, hardware, network, commands, and raw metrics. Model artifacts use configured mounted-drive storage and never `/home`.
|
||||
- Preserve existing Transformers behavior and backend-agnostic Tracker routing/load balancing/billing/relay semantics unless an explicit versioned contract says otherwise. One scoped story commit is expected during execution, but this specification-materialization change is not committed.
|
||||
|
||||
## Evidence handoff
|
||||
|
||||
Write and verify `.scratch/distributed-gguf-runtime/evidence/DGR-068/README.md`. Until every criterion and applicable gate has real evidence, this story remains `passes: false`. Legacy evidence is provenance only, not completion credit.
|
||||
@@ -0,0 +1,39 @@
|
||||
<!-- GENERATED FROM prd.json — DO NOT EDIT AS AN INDEPENDENT SOURCE. prd.json IS AUTHORITATIVE. -->
|
||||
# DGR-069: Prepare narrow upstream llama.cpp collaboration patches
|
||||
|
||||
- **Status / triage:** specification only; `ready-for-human`; `passes: false`
|
||||
- **Execution mode:** `HITL`
|
||||
- **Milestone:** `M5`
|
||||
- **Dependencies:** `DGR-028`, `DGR-035`, `DGR-038`, `DGR-051`
|
||||
- **Blocks (derived):** `DGR-071`
|
||||
- **Labels:** `area:upstream`, `area:patches`, `type:collaboration`, `priority:p2`, `gate:hitl`, `ready-for-human`
|
||||
- **Evidence class:** `release`
|
||||
- **Hardware:** `none`
|
||||
- **Model:** `generic+deepseek-v4`
|
||||
- **Upstream:** `yes`
|
||||
|
||||
## Objective / description
|
||||
|
||||
Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`, source issue `.scratch/distributed-gguf-runtime/issues/069-prepare-narrow-upstream-llama-cpp-collaboration-patches.md`, and evidence READMEs for dependencies (DGR-028, DGR-035, DGR-038, DGR-051) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Reduce long-term patch burden through generic upstreamable hooks without asking llama.cpp to own Meshnet.
|
||||
|
||||
## Acceptance criteria
|
||||
|
||||
- [ ] Separate generic range loading, boundary I/O, and filtered state hooks from project worker/protocol code.
|
||||
- [ ] Provide one scoped patch, focused test, and minimal reproducer per concern against the exact upstream pin.
|
||||
- [ ] Compare the proposal with prior-art evidence and current upstream V4 support/maturity.
|
||||
- [ ] Prepare human-ready design/outreach text; actual issue/PR submission remains a human action.
|
||||
- [ ] Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff.
|
||||
|
||||
## Shared quality gates
|
||||
|
||||
- Targeted deterministic tests pass; Python changes also pass `python -m compileall packages tests`.
|
||||
- `git diff --check` passes.
|
||||
- Default tests are model-download-free, API-credit-free, and GPU-free.
|
||||
- Evidence README records exact changed files, commands/results, limitations, and dependency handoff; no fabricated evidence or inherited completion credit.
|
||||
- Native changes pass focused out-of-tree CMake build and CTest; patch changes verify clean apply/check/reverse against the exact llama.cpp pin.
|
||||
- Runs are opt-in and record exact artifact/split hashes, runtime/upstream pin, backend/driver, hardware, network, commands, and raw metrics. Model artifacts use configured mounted-drive storage and never `/home`.
|
||||
- Preserve existing Transformers behavior and backend-agnostic Tracker routing/load balancing/billing/relay semantics unless an explicit versioned contract says otherwise. One scoped story commit is expected during execution, but this specification-materialization change is not committed.
|
||||
|
||||
## Evidence handoff
|
||||
|
||||
Write and verify `.scratch/distributed-gguf-runtime/evidence/DGR-069/README.md`. Until every criterion and applicable gate has real evidence, this story remains `passes: false`. Legacy evidence is provenance only, not completion credit.
|
||||
@@ -0,0 +1,39 @@
|
||||
<!-- GENERATED FROM prd.json — DO NOT EDIT AS AN INDEPENDENT SOURCE. prd.json IS AUTHORITATIVE. -->
|
||||
# DGR-070: Enforce the DeepSeek V4 Flash beta gate
|
||||
|
||||
- **Status / triage:** specification only; `ready-for-human`; `passes: false`
|
||||
- **Execution mode:** `HITL`
|
||||
- **Milestone:** `M5`
|
||||
- **Dependencies:** `DGR-057`, `DGR-059`, `DGR-060`, `DGR-062`, `DGR-064`, `DGR-066`, `DGR-067`, `DGR-068`
|
||||
- **Blocks (derived):** `DGR-071`
|
||||
- **Labels:** `area:deepseek-v4`, `area:release`, `milestone:beta`, `priority:p0`, `gate:hitl`, `ready-for-human`
|
||||
- **Evidence class:** `release`
|
||||
- **Hardware:** `required`
|
||||
- **Model:** `deepseek-v4-flash`
|
||||
- **Upstream:** `yes`
|
||||
|
||||
## Objective / description
|
||||
|
||||
Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`, source issue `.scratch/distributed-gguf-runtime/issues/070-enforce-the-deepseek-v4-flash-beta-gate.md`, and evidence READMEs for dependencies (DGR-057, DGR-059, DGR-060, DGR-062, DGR-064, DGR-066, DGR-067, DGR-068) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Promote beta only after concurrency, resilience, long-context, MTP, scale, packaging, and speed gates pass.
|
||||
|
||||
## Acceptance criteria
|
||||
|
||||
- [ ] Evaluate all beta metrics against DGF-004 without changing thresholds after observing results.
|
||||
- [ ] Require V4 parity, batching/fairness, bounded backpressure, failure recovery, long-context correctness, MTP evidence, and dynamic 10+ stage evidence.
|
||||
- [ ] Publish the exact certified hardware/backend/recipe matrix; all other lanes remain dark.
|
||||
- [ ] Decision is `beta`, `targeted optimization`, or `stop/rollback`, with unresolved failures listed explicitly.
|
||||
- [ ] Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff.
|
||||
|
||||
## Shared quality gates
|
||||
|
||||
- Targeted deterministic tests pass; Python changes also pass `python -m compileall packages tests`.
|
||||
- `git diff --check` passes.
|
||||
- Default tests are model-download-free, API-credit-free, and GPU-free.
|
||||
- Evidence README records exact changed files, commands/results, limitations, and dependency handoff; no fabricated evidence or inherited completion credit.
|
||||
- Native changes pass focused out-of-tree CMake build and CTest; patch changes verify clean apply/check/reverse against the exact llama.cpp pin.
|
||||
- Runs are opt-in and record exact artifact/split hashes, runtime/upstream pin, backend/driver, hardware, network, commands, and raw metrics. Model artifacts use configured mounted-drive storage and never `/home`.
|
||||
- Preserve existing Transformers behavior and backend-agnostic Tracker routing/load balancing/billing/relay semantics unless an explicit versioned contract says otherwise. One scoped story commit is expected during execution, but this specification-materialization change is not committed.
|
||||
|
||||
## Evidence handoff
|
||||
|
||||
Write and verify `.scratch/distributed-gguf-runtime/evidence/DGR-070/README.md`. Until every criterion and applicable gate has real evidence, this story remains `passes: false`. Legacy evidence is provenance only, not completion credit.
|
||||
@@ -0,0 +1,39 @@
|
||||
<!-- GENERATED FROM prd.json — DO NOT EDIT AS AN INDEPENDENT SOURCE. prd.json IS AUTHORITATIVE. -->
|
||||
# DGR-071: Establish upstream pin, patch, and certification maintenance
|
||||
|
||||
- **Status / triage:** specification only; `ready-for-agent`; `passes: false`
|
||||
- **Execution mode:** `AFK`
|
||||
- **Milestone:** `M5`
|
||||
- **Dependencies:** `DGR-069`, `DGR-070`
|
||||
- **Blocks (derived):** None
|
||||
- **Labels:** `area:maintenance`, `area:upstream`, `area:certification`, `type:operations`, `priority:p2`, `ready-for-agent`
|
||||
- **Evidence class:** `release`
|
||||
- **Hardware:** `optional`
|
||||
- **Model:** `deepseek-v4-flash`
|
||||
- **Upstream:** `yes`
|
||||
|
||||
## Objective / description
|
||||
|
||||
Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`, source issue `.scratch/distributed-gguf-runtime/issues/071-establish-upstream-pin-patch-and-certification-maintenance.md`, and evidence READMEs for dependencies (DGR-069, DGR-070) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Keep beta reproducible and detect upstream/model/hardware drift before it reaches routable nodes.
|
||||
|
||||
## Acceptance criteria
|
||||
|
||||
- [ ] Add a documented update procedure for llama.cpp pin, numbered patches, protocol/engine versions, V4 target revision, and certification records.
|
||||
- [ ] A candidate pin update must apply/build/test in isolation and cannot replace the production pin automatically.
|
||||
- [ ] Any changed graph, tensor inventory, boundary, cache/state layout, backend behavior, or performance invalidates affected certification.
|
||||
- [ ] Add scheduled model-free checks plus opt-in real-hardware recertification instructions and rollback procedure.
|
||||
- [ ] Applicable shared quality gates in `prd.json` pass, and the evidence handoff records exact commands/results, changed files, limitations, and dependency handoff.
|
||||
|
||||
## Shared quality gates
|
||||
|
||||
- Targeted deterministic tests pass; Python changes also pass `python -m compileall packages tests`.
|
||||
- `git diff --check` passes.
|
||||
- Default tests are model-download-free, API-credit-free, and GPU-free.
|
||||
- Evidence README records exact changed files, commands/results, limitations, and dependency handoff; no fabricated evidence or inherited completion credit.
|
||||
- Native changes pass focused out-of-tree CMake build and CTest; patch changes verify clean apply/check/reverse against the exact llama.cpp pin.
|
||||
- Runs are opt-in and record exact artifact/split hashes, runtime/upstream pin, backend/driver, hardware, network, commands, and raw metrics. Model artifacts use configured mounted-drive storage and never `/home`.
|
||||
- Preserve existing Transformers behavior and backend-agnostic Tracker routing/load balancing/billing/relay semantics unless an explicit versioned contract says otherwise. One scoped story commit is expected during execution, but this specification-materialization change is not committed.
|
||||
|
||||
## Evidence handoff
|
||||
|
||||
Write and verify `.scratch/distributed-gguf-runtime/evidence/DGR-071/README.md`. Until every criterion and applicable gate has real evidence, this story remains `passes: false`. Legacy evidence is provenance only, not completion credit.
|
||||
Reference in New Issue
Block a user