nopperl 4bbfc36b16 [V1] Hybrid allocator without prefix caching (#20661) ...

Signed-off-by: nopperl <54780682+nopperl@users.noreply.github.com>

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

..

sched

[Sched] Enhance the logic to remove stopped requests from queues (#20739)

2025-07-12 15:33:13 -07:00

__init__.py

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

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

block_pool.py

[Core] Use tuple for kv cache group block ids (#19175)

2025-06-10 07:01:17 +02:00

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

[Misc] Simplify the prefix caching logic on draft tokens (#20701)

2025-07-09 14:48:35 -07:00

kv_cache_utils.py

Enable V1 for Hybrid SSM/Attention Models (#20016)

2025-07-04 17:46:53 +00:00

single_type_kv_cache_manager.py

[v1] Support mamba2 (#19327)

2025-06-18 20:34:15 +00:00