DGR-055: Implement compatible continuous decode batching #39

New Issue

popov · 2026-07-16T20:36:06Z

popov commented

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

DGR-055: Implement compatible continuous decode batching

Status / triage: specification only; ready-for-agent; passes: false
Execution mode: AFK
Milestone: M4
Dependencies: DGR-038, DGR-040, DGR-054
Blocks (derived): DGR-056, DGR-057
Labels: area:scheduler, area:batching, type:performance, priority:p1, ready-for-agent
Evidence class: fixture
Hardware: none
Model: generic
Upstream: no

Objective / description

Fresh Ralph session: read .scratch/distributed-gguf-runtime/RALPH-CONTEXT.md, source issue .scratch/distributed-gguf-runtime/issues/055-implement-compatible-continuous-decode-batching.md, and evidence READMEs for dependencies (DGR-038, DGR-040, DGR-054) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Batch compatible active sessions without violating route, recipe, position, or architecture state.

Acceptance criteria

Batch only sessions with compatible engine, recipe, phase, boundary schema, and state layout.
Preserve per-session positions, sequence IDs, outputs, cancellation, and accounting.
Decode receives bounded service while prefill remains schedulable.
Deterministic 1/2/4/8 concurrency tests show no cross-session corruption.
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-055/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-055: Implement compatible continuous decode batching - **Status / triage:** specification only; `ready-for-agent`; `passes: false` - **Execution mode:** `AFK` - **Milestone:** `M4` - **Dependencies:** `DGR-038`, `DGR-040`, `DGR-054` - **Blocks (derived):** `DGR-056`, `DGR-057` - **Labels:** `area:scheduler`, `area:batching`, `type:performance`, `priority:p1`, `ready-for-agent` - **Evidence class:** `fixture` - **Hardware:** `none` - **Model:** `generic` - **Upstream:** `no` ## Objective / description Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`, source issue `.scratch/distributed-gguf-runtime/issues/055-implement-compatible-continuous-decode-batching.md`, and evidence READMEs for dependencies (DGR-038, DGR-040, DGR-054) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Batch compatible active sessions without violating route, recipe, position, or architecture state. ## Acceptance criteria - [ ] Batch only sessions with compatible engine, recipe, phase, boundary schema, and state layout. - [ ] Preserve per-session positions, sequence IDs, outputs, cancellation, and accounting. - [ ] Decode receives bounded service while prefill remains schedulable. - [ ] Deterministic 1/2/4/8 concurrency tests show no cross-session corruption. - [ ] 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-055/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 20:36:06 +00:00

popov added the area:scheduler area:batching type:performance priority:p1 ready-for-agent status:blocked 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#39