DGR-066: Implement and benchmark V4 MTP #50

New Issue

popov · 2026-07-16T20:36:07Z

popov commented

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

DGR-066: Implement and benchmark V4 MTP

Status / triage: specification only; ready-for-agent; passes: false
Execution mode: AFK
Milestone: M4
Dependencies: DGR-054, DGR-060, DGR-064, DGR-065
Blocks (derived): DGR-067, DGR-070
Labels: area:deepseek-v4, area:mtp, type:runtime, 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/066-implement-and-benchmark-v4-mtp.md, and evidence READMEs for dependencies (DGR-054, DGR-060, DGR-064, DGR-065) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Implement the locked MTP contract around upstream llama.cpp before beta, without making MTP an alpha prerequisite.

Acceptance criteria

Implement the exact DGR-065 MTP ownership and typed state contract against the pinned upstream V4 graph while preserving shard-local caches.
Pass whole-model versus ranged MTP correctness, accepted-token, rejection, rollback/truncation, and session-isolation tests.
Benchmark MTP-off versus MTP-on quality, accepted-token rate, TTFT, decode speed, seam bytes, and memory on the locked lane.
Distinguish implemented, certified, disabled, and unsupported MTP recipes in fail-closed capability 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-066/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-066: Implement and benchmark V4 MTP - **Status / triage:** specification only; `ready-for-agent`; `passes: false` - **Execution mode:** `AFK` - **Milestone:** `M4` - **Dependencies:** `DGR-054`, `DGR-060`, `DGR-064`, `DGR-065` - **Blocks (derived):** `DGR-067`, `DGR-070` - **Labels:** `area:deepseek-v4`, `area:mtp`, `type:runtime`, `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/066-implement-and-benchmark-v4-mtp.md`, and evidence READMEs for dependencies (DGR-054, DGR-060, DGR-064, DGR-065) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Implement the locked MTP contract around upstream llama.cpp before beta, without making MTP an alpha prerequisite. ## Acceptance criteria - [ ] Implement the exact DGR-065 MTP ownership and typed state contract against the pinned upstream V4 graph while preserving shard-local caches. - [ ] Pass whole-model versus ranged MTP correctness, accepted-token, rejection, rollback/truncation, and session-isolation tests. - [ ] Benchmark MTP-off versus MTP-on quality, accepted-token rate, TTFT, decode speed, seam bytes, and memory on the locked lane. - [ ] Distinguish implemented, certified, disabled, and unsupported MTP recipes in fail-closed capability 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-066/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 type:runtime priority:p1 area:mtp status:blocked ready-for-agent area:deepseek-v4 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#50