DGR-054: Enforce the DeepSeek V4 Flash alpha gate #38

New Issue

popov · 2026-07-16T20:36:06Z

popov commented

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

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.

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.

# 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. ## 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.

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

popov added the area:release milestone:alpha gate:hitl ready-for-human area:deepseek-v4 status:blocked priority:p0 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#38