DGR-063: Profile and optimize the critical seam #47

New Issue

popov · 2026-07-16T20:36:07Z

popov commented

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

DGR-063: Profile and optimize the critical seam

Status / triage: specification only; ready-for-agent; passes: false
Execution mode: AFK
Milestone: M4
Dependencies: DGR-057, DGR-061
Blocks (derived): DGR-064
Labels: area:performance, type:optimization, priority:p1, ready-for-agent
Evidence class: real-hardware
Hardware: required
Model: generic
Upstream: conditional

Objective / description

Fresh Ralph session: read .scratch/distributed-gguf-runtime/RALPH-CONTEXT.md, source issue .scratch/distributed-gguf-runtime/issues/063-profile-and-optimize-the-critical-seam.md, and evidence READMEs for dependencies (DGR-057, DGR-061) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Optimize only the measured dominant compute, serialization, copy, or transport bottleneck.

Acceptance criteria

Profile worker compute, tensor conversion, copies, protobuf framing, compression, relay/direct transport, queueing, and synchronization.
Select one dominant bottleneck from evidence and lock its before/after benchmark.
Implement one bounded optimization without weakening correctness or protocol identity.
Report whether the optimization changes TTFT, prefill, decode, throughput, or memory and preserve raw data.
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-063/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-063: Profile and optimize the critical seam - **Status / triage:** specification only; `ready-for-agent`; `passes: false` - **Execution mode:** `AFK` - **Milestone:** `M4` - **Dependencies:** `DGR-057`, `DGR-061` - **Blocks (derived):** `DGR-064` - **Labels:** `area:performance`, `type:optimization`, `priority:p1`, `ready-for-agent` - **Evidence class:** `real-hardware` - **Hardware:** `required` - **Model:** `generic` - **Upstream:** `conditional` ## Objective / description Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`, source issue `.scratch/distributed-gguf-runtime/issues/063-profile-and-optimize-the-critical-seam.md`, and evidence READMEs for dependencies (DGR-057, DGR-061) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Optimize only the measured dominant compute, serialization, copy, or transport bottleneck. ## Acceptance criteria - [ ] Profile worker compute, tensor conversion, copies, protobuf framing, compression, relay/direct transport, queueing, and synchronization. - [ ] Select one dominant bottleneck from evidence and lock its before/after benchmark. - [ ] Implement one bounded optimization without weakening correctness or protocol identity. - [ ] Report whether the optimization changes TTFT, prefill, decode, throughput, or memory and preserve raw data. - [ ] 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-063/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 area:performance priority:p1 type:optimization status:blocked ready-for-agent 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#47