DGR-038: Implement isolated shard-local Hot KV State #22

New Issue

popov · 2026-07-16T20:36:03Z

popov commented

2026-07-16 20:36:03 +00:00

DGR-038: Implement isolated shard-local Hot KV State

Status / triage: specification only; ready-for-agent; passes: false
Execution mode: AFK
Milestone: M2
Dependencies: DGR-037
Blocks (derived): DGR-039, DGR-052, DGR-055, DGR-069
Labels: area:kv-cache, area:concurrency, type:runtime, priority:p0, ready-for-agent
Evidence class: real-model
Hardware: optional
Model: dense-llama
Upstream: yes

Objective / description

Fresh Ralph session: read .scratch/distributed-gguf-runtime/RALPH-CONTEXT.md, source issue .scratch/distributed-gguf-runtime/issues/038-implement-isolated-shard-local-hot-kv-state.md, and evidence READMEs for dependencies (DGR-037) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Map each route session and epoch to isolated state containing only locally owned layers.

Acceptance criteria

Map (route_session_id, route_epoch) to an isolated llama sequence or bounded context.
Support prefill/decode append, truncate, release, TTL/LRU eviction, cache miss, and stale-epoch rejection.
Four concurrent sessions complete without token, KV, position, or cancellation cross-talk.
Release/eviction returns memory to the configured budget without affecting other sessions.
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-038/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-038: Implement isolated shard-local Hot KV State - **Status / triage:** specification only; `ready-for-agent`; `passes: false` - **Execution mode:** `AFK` - **Milestone:** `M2` - **Dependencies:** `DGR-037` - **Blocks (derived):** `DGR-039`, `DGR-052`, `DGR-055`, `DGR-069` - **Labels:** `area:kv-cache`, `area:concurrency`, `type:runtime`, `priority:p0`, `ready-for-agent` - **Evidence class:** `real-model` - **Hardware:** `optional` - **Model:** `dense-llama` - **Upstream:** `yes` ## Objective / description Fresh Ralph session: read `.scratch/distributed-gguf-runtime/RALPH-CONTEXT.md`, source issue `.scratch/distributed-gguf-runtime/issues/038-implement-isolated-shard-local-hot-kv-state.md`, and evidence READMEs for dependencies (DGR-037) before changing code. Inspect live source/tests rather than trusting legacy pass states. Objective: Map each route session and epoch to isolated state containing only locally owned layers. ## Acceptance criteria - [ ] Map `(route_session_id, route_epoch)` to an isolated llama sequence or bounded context. - [ ] Support prefill/decode append, truncate, release, TTL/LRU eviction, cache miss, and stale-epoch rejection. - [ ] Four concurrent sessions complete without token, KV, position, or cancellation cross-talk. - [ ] Release/eviction returns memory to the configured budget without affecting other sessions. - [ ] 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-038/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 M2 milestone 2026-07-16 20:36:03 +00:00

popov added the area:kv-cache area:concurrency type:runtime ready-for-agent priority:p0 status:blocked labels 2026-07-16 20:36:03 +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#22