DGR-047: Adapt the upstream V4 mHC boundary for ranged ownership #31

New Issue

popov · 2026-07-16T20:36:05Z

popov commented

2026-07-16 20:36:05 +00:00

DGR-047: Adapt the upstream V4 mHC boundary for ranged ownership

Status / triage: specification only; ready-for-agent; passes: false
Execution mode: AFK
Milestone: M3
Dependencies: DGR-045, DGR-046
Blocks (derived): DGR-048, DGR-049, DGR-050, DGR-051
Labels: area:deepseek-v4, area:mhc, 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/047-adapt-the-upstream-v4-mhc-boundary-for-ranged-ownership.md, and evidence READMEs for dependencies (DGR-045, DGR-046) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Add range-boundary adapters around upstream llama.cpp V4 mHC execution without reimplementing the V4 graph or kernels.

Acceptance criteria

Represent and validate the upstream V4 4×4096 mHC boundary without flattening semantic axes.
Add only head/intermediate/tail range ownership and boundary conversion hooks around the pinned upstream llama.cpp graph.
Compare deterministic fixture vectors and single-process ranged outputs with upstream whole-model execution.
Document that llama.cpp owns V4 mHC graph/kernels and that quantized storage does not alter the logical boundary schema.
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-047/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-047: Adapt the upstream V4 mHC boundary for ranged ownership - **Status / triage:** specification only; `ready-for-agent`; `passes: false` - **Execution mode:** `AFK` - **Milestone:** `M3` - **Dependencies:** `DGR-045`, `DGR-046` - **Blocks (derived):** `DGR-048`, `DGR-049`, `DGR-050`, `DGR-051` - **Labels:** `area:deepseek-v4`, `area:mhc`, `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/047-adapt-the-upstream-v4-mhc-boundary-for-ranged-ownership.md`, and evidence READMEs for dependencies (DGR-045, DGR-046) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Add range-boundary adapters around upstream llama.cpp V4 mHC execution without reimplementing the V4 graph or kernels. ## Acceptance criteria - [ ] Represent and validate the upstream V4 4×4096 mHC boundary without flattening semantic axes. - [ ] Add only head/intermediate/tail range ownership and boundary conversion hooks around the pinned upstream llama.cpp graph. - [ ] Compare deterministic fixture vectors and single-process ranged outputs with upstream whole-model execution. - [ ] Document that llama.cpp owns V4 mHC graph/kernels and that quantized storage does not alter the logical boundary schema. - [ ] 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-047/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 20:36:05 +00:00

popov added the area:mhc type:runtime area:deepseek-v4 ready-for-agent priority:p0 status:blocked labels 2026-07-16 20:36:05 +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#31