Skip to content

feat: support cache-off ATOM PD with one KV block #237

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
gspark-etri wants to merge 1 commit into from
Closed

feat: support cache-off ATOM PD with one KV block #237

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 4 additions & 0 deletions opt_prime/examples/pd/http_matrix/STATUS.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,3 +13,7 @@ Gemma full-prefix KV imports now run through ATOM PD scheduling: 33 CPU tests an
Geometry recovery follow-up: malformed remote heads/KV lengths fail only their request; real device import failures still poison the scheduler.37related tests pass. Hardware evidence remains c76e03a.

Long hardware follow-up on1e54786:6423–6428token inputs,10normal/reuse HTTP responses match nativeATOM;12remote/0local prefills including cancellation. Recorded RNGD KV replay, arithmetic wrong on both native/imported paths; no quality or live-transfer claim.

## Single-block static PD (#236)

Static B1 with one KV block now supports cache-off full-prefix PD. KONI live RNGD->ATOM HTTP14/14 output checks and16remote/0local prefills pass, including cancel/disconnect reuse.43CPU tests cover queued reuse, late cancellation and partial-prefix error recovery; cache/multi-lane guards remain. No new artifact, hardware batch or cache-restoration claim. See single-block-pd236 record and evidence236.
1 change: 1 addition & 0 deletions opt_prime/examples/pd/http_matrix/evidence236/events.jsonl
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1 @@
{"id": "3352f09cfbc74d869aefd49b13ae2cc7", "ts": "2026-10-23T22:53:49+09:00", "task": "Single-block ATOM PD (aicomp #236)", "result": "Static B1 cache-off KONI live PD enabled without extra KV block:14/14 HTTP outputs exact,16remote/0local; cancel/disconnect reuse pass.43CPU tests incl partial/late-cancel recovery; unsupported cache/multi-lane still rejected.", "next": "Publish scoped scheduler PR; continue medium live matrix and wider performance/cache coverage.", "state": "active", "done": false, "blocker": "", "metrics": {}, "params": {"model": "KONI-8B", "batch": "1", "kv_blocks": "1"}, "artifacts": ["opt_prime/examples/pd/http_matrix/evidence236/koni-live-http.json"], "experiments": ["opt_prime/examples/pd/http_matrix/experiments/2026-10-23-single-block-pd236.md"], "labels": ["experiment"], "review": true, "todos": [], "note": "", "agent": "codex", "host": "RNGD+ATOM host", "branch": "main", "commit": "351d39d-dirty"}
Loading