40 lines
3.2 KiB
Markdown
40 lines
3.2 KiB
Markdown
<!-- 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.
|