Raushan Turganbay f38ee34a0a [feat] Enable mm caching for transformers backend (#21358) ...

Signed-off-by: raushan <raushan@huggingface.co>

2025-07-22 08:18:46 -07:00

..

sched

Implement Async Scheduling (#19970)

2025-07-14 23:01:46 -07:00

__init__.py

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

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

block_pool.py

[Core] Introduce popleft_n and append_n in FreeKVCacheBlockQueue to further optimize block_pool (#21222)

2025-07-22 06:17:47 -07:00

encoder_cache_manager.py

[V1] Add API docs for EncoderCacheManager (#19294)

2025-06-18 13:37:01 +08:00

kv_cache_coordinator.py

[V1] Hybrid allocator without prefix caching (#20661)

2025-07-13 16:55:14 +00:00

kv_cache_manager.py

[v1][core] Support for attention free models (#20811)

2025-07-15 14:20:01 +00:00

kv_cache_utils.py

[feat] Enable mm caching for transformers backend (#21358)

2025-07-22 08:18:46 -07:00

single_type_kv_cache_manager.py

[Core] Support Local Chunked Attention for Hybrid KV Cache (#19351)

2025-07-18 20:48:38 -07:00