Jialin Ouyang 4f8c4b890a [Core] Use KVCacheBlock as much as possible instead of dict[block_id, KVCacheBlock] (#24830) ...

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

2025-09-23 15:11:14 -07:00

..

sched

[Core] Drop overly aggressive whisper assertion (#25408)

2025-09-22 17:09:52 -07:00

__init__.py

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

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

block_pool.py

[Core] Use KVCacheBlock as much as possible instead of dict[block_id, KVCacheBlock] (#24830)

2025-09-23 15:11:14 -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

[Doc] Fix cross-reference warnings (#25058)

2025-09-18 02:05:16 -07:00

kv_cache_utils.py

[Docs] Fix warnings in mkdocs build (continued) (#25042)

2025-09-20 11:45:18 +00:00

single_type_kv_cache_manager.py

Add the support for the qwen3 next model (a hybrid attention model). (#24526)

2025-09-11 15:32:09 +08:00