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