DGR-053: Certify a real 2–4-stage V4 route #37

New Issue

popov · 2026-07-16T20:36:06Z

popov commented

2026-07-16 20:36:06 +00:00

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.

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.

# 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. ## 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.

popov added this to the M3 milestone 2026-07-16 20:36:06 +00:00

popov added the gate:hitl ready-for-human area:hardware area:deepseek-v4 status:blocked priority:p0 type:certification labels 2026-07-16 20:36:06 +00:00

Sign in to join this conversation.

1 Participants

Notifications

Due Date

No due date set.

Dependencies

No dependencies set.

Reference: popov/neuron-tai#37