Repository navigation
feat: support cache-off ATOM PD with one KV block - #237
Draft
gspark-etri wants to merge 1 commit into
Draft
gspark-etri wants to merge 1 commit into
gspark-etri wants to merge 1 commit into
Conversation
This was referenced Oct 23, 2026
gspark-etri
added a commit
that referenced
this pull request
Oct 30, 2026
Lane-local sliding cache tables and global block tables for hybrid (Gemma3) external-cache serving; fresh full-prefix hybrid PD; batch-1 single-block PD with prefix/host caching off. Hybrid prefix and host caching stay rejected. From feat/236-atom-single-pd (#210, #232, #237): atom/batching.py, tests/test_atom_hybrid.py, tests/test_atom_batching.py. ATOM.md section rewritten to the supported scope. Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Background
KONI's validated static B1 ATOM artifact has one KV block. The scheduler previously required an extra scratch block even for cache-off PD, preventing live remote prefill with that artifact.
Changes
Allow block0 to be assigned and released for exactly one non-hybrid lane when prefix/host caches are off. There is no simultaneous idle decoding lane in this configuration. Require full-prefix results, isolate partial-result errors per request, and keep existing multi-lane/cache/hybrid guards.
Verification
Compatibility and limits
Stacked on #232; hardware harness/producer in #235 and SIGPIPE-safe HTTP module from #215. No extra model compilation or communication protocol change. Prefix/host cache, hybrid single-block and multi-lane single-block paths remain unsupported. Broader live long-context, performance and overlap work remains open under #201/#234.
Related Issue
Closes #236. Related #201/#231/#234.