Jialin Ouyang 201c971e96 [Perf][Easy] Early stop in request_block_hasher (#26112) ...

Signed-off-by: Jialin Ouyang <Jialin.Ouyang@gmail.com>

2025-10-05 16:46:03 +08:00

..

sched

[Core] Enable decode of context length equal to max model length (#26168)

2025-10-04 09:59:26 +00:00

__init__.py

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

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

block_pool.py

[V1] [P/D] Add Support for KV Load Failure Recovery (#19330)

2025-09-30 14:57:08 -07:00

encoder_cache_manager.py

[Multimodal] Remove legacy multimodal fields in favor of MultiModalFeatureSpec (#24548)

2025-09-12 21:42:23 +08:00

kv_cache_coordinator.py

[Feature] Support Decode Context Parallel (DCP) for MLA (#23734)

2025-09-06 13:24:05 +08:00

kv_cache_manager.py

[Core] Don't count preempted tokens in prefix cache hit rate (#25787)

2025-09-27 00:16:40 +00:00

kv_cache_utils.py

[Perf][Easy] Early stop in request_block_hasher (#26112)

2025-10-05 16:46:03 +08:00

single_type_kv_cache_manager.py

[V1] [Hybrid] Mamba2 Automatic Prefix Caching (#25752)

2025-10-04 06:34:22 +02:00