DGR-056: Enforce bounded admission, queues, and backpressure #40

New Issue

popov · 2026-07-16T20:36:06Z

popov commented

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

DGR-056: Enforce bounded admission, queues, and backpressure

Status / triage: specification only; ready-for-agent; passes: false
Execution mode: AFK
Milestone: M4
Dependencies: DGR-055
Blocks (derived): DGR-057, DGR-058, DGR-060
Labels: area:scheduler, area:backpressure, 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/056-enforce-bounded-admission-queues-and-backpressure.md, and evidence READMEs for dependencies (DGR-055) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Prevent weight, KV, state, scratch, and stream buffers from exceeding admitted capacity.

Acceptance criteria

Admission accounts separately for weights, KV/state, scratch, in-flight fragments, and queue slots.
Queue and stream limits produce structured retryable or terminal responses.
Prefill cannot starve decode and one route session cannot monopolize queue capacity.
Telemetry reports active sessions, queue depth/time, batch occupancy, memory pressure, and rejects.
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-056/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-056: Enforce bounded admission, queues, and backpressure - **Status / triage:** specification only; `ready-for-agent`; `passes: false` - **Execution mode:** `AFK` - **Milestone:** `M4` - **Dependencies:** `DGR-055` - **Blocks (derived):** `DGR-057`, `DGR-058`, `DGR-060` - **Labels:** `area:scheduler`, `area:backpressure`, `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/056-enforce-bounded-admission-queues-and-backpressure.md`, and evidence READMEs for dependencies (DGR-055) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Prevent weight, KV, state, scratch, and stream buffers from exceeding admitted capacity. ## Acceptance criteria - [ ] Admission accounts separately for weights, KV/state, scratch, in-flight fragments, and queue slots. - [ ] Queue and stream limits produce structured retryable or terminal responses. - [ ] Prefill cannot starve decode and one route session cannot monopolize queue capacity. - [ ] Telemetry reports active sessions, queue depth/time, batch occupancy, memory pressure, and rejects. - [ ] 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-056/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:backpressure area:scheduler 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#40