fix(kvflash): pooled prefix snapshot at chunk boundary (≥128K restore)#445

Closed

dusterbloom wants to merge 9 commits into

Luce-Org:mainfrom

dusterbloom:pr/kvflash-cache-persistence

Commits on Jun 24, 2026

feat(kvflash): pager serialize/deserialize + critical-chunk pinning
dusterbloom
committed
feat(qwen35moe): pooled chunked prefill + pooled snapshot/restore over KVFlash
dusterbloom
committed
refactor(qwen35moe): dedup chunked-prefill loops + inline for_each_segment
dusterbloom
committed
fix(kvflash): save pooled prefix snapshot at chunk boundary so ≥128K restore works
dusterbloom
committed
test(server): cold_prefix_boundary returns 4000 after layout_known_ guard removal
dusterbloom
committed
ci: re-trigger (prior RTX GPU job cancelled by self-hosted-runner GPU contention)
dusterbloom
committed
fix(cubic): address production P1/P2 review findings (bounded loop, OOB, UAF, atoi-UB, re-prefill fallback, pin_range, gguf type guards)
dusterbloom
committed

Commits on Jun 30, 2026