3 people e6fc81bc78 [Bugfix][Scheduler] Let pooling chunked prefill use full context (#48039) ...

Signed-off-by: Tommy <tran.tommy@hotmail.com>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>

2026-10-07 07:32:00 +00:00

..

sched

[Bugfix][Scheduler] Let pooling chunked prefill use full context (#48039)

2026-10-07 07:32:00 +00:00

__init__.py

[V1] Implement vLLM V1 [1/N] (#9289)

2024-10-22 01:24:07 -07:00

block_pool.py

Fix grammar in BlockPool.reset_prefix_cache docstring: "to invalid" → "to invalidate" (#59886)

2026-10-06 10:19:54 +00:00

encoder_cache_manager.py

[Bugfix][V1] Reject encoder-cache hits with mismatched embedding counts (#57696)

2026-09-24 08:40:47 +00:00

kv_cache_coordinator.py

[Bugfix][KV Offload] Honor speculative cacheability in SimpleCPU (#60071)

2026-10-06 14:25:08 +02:00

kv_cache_manager.py

[Bugfix][Core] Exempt exactly the blocks an async KV load writes from zeroing (#59504)

2026-10-03 06:26:12 +00:00

kv_cache_metrics.py

[Core][Observability] Add KV cache residency metrics (#27793)

2025-12-01 18:27:53 +00:00

kv_cache_utils.py

[Bugfix][HiSparse] Size the KV cache from the groups HiSparse allocates (#59450)

2026-10-02 04:11:55 +00:00

single_type_kv_cache_manager.py

[Bugfix][Core] Retire stale Mamba spec blocks in prefill checkpoint steps (#59759)

2026-10-06 11:01:19 +08:00