DGR-062: Certify a dynamic real 10+ stage V4 scenario #46

New Issue

popov · 2026-07-16T20:36:07Z

popov commented

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

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.

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.

# 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. ## 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.

popov added this to the M4 milestone 2026-07-16 20:36:07 +00:00

popov added the gate:hitl area:hardware ready-for-human priority:p1 status:blocked type:certification area:deepseek-v4 area:scale labels 2026-07-16 20:36:07 +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#46