Woosuk Kwon 9b459eca88 [V1][Scheduler] Avoid calling _try_schedule_encoder_inputs for every request (#15778) ...

Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>

2025-03-30 14:10:42 -07:00

..

sched

[V1][Scheduler] Avoid calling _try_schedule_encoder_inputs for every request (#15778)

2025-03-30 14:10:42 -07:00

__init__.py

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

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

block_pool.py

Support SHA256 as hash function in prefix caching (#15297)

2025-03-26 11:11:28 -07:00

encoder_cache_manager.py

[Misc] Avoid direct access of global mm_registry in compute_encoder_budget (#15621)

2025-03-27 17:52:00 +00:00

kv_cache_manager.py

Support SHA256 as hash function in prefix caching (#15297)

2025-03-26 11:11:28 -07:00

kv_cache_utils.py

Support SHA256 as hash function in prefix caching (#15297)

2025-03-26 11:11:28 -07:00