vllm/v1 at bf0560bda98bc664d5fe3a66440417e5cd483c53 - vllm

mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-07-19 15:17:15 +08:00

History

Reinstate best_of for V0 (#14356 )

Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>

2025-03-06 08:34:22 -08:00

attention

[Kernel] [V1] Improved performance for V1 Triton (ROCm) backend (#14152 )

2025-03-06 07:39:16 -08:00

core

Update deprecated Python 3.8 typing (#13971 )

2025-03-02 17:34:51 -08:00

engine

Reinstate best_of for V0 (#14356 )

2025-03-06 08:34:22 -08:00

executor

Update deprecated Python 3.8 typing (#13971 )

2025-03-02 17:34:51 -08:00

metrics

[V1][Bugfix] Do not reset prefix caching metrics (#14235 )

2025-03-05 04:39:13 +00:00

sample

Update deprecated Python 3.8 typing (#13971 )

2025-03-02 17:34:51 -08:00

spec_decode

[V1][Spec Decode] Optimize N-gram matching with Numba (#13365 )

2025-02-18 13:19:58 -08:00

stats

Update deprecated Python 3.8 typing (#13971 )

2025-03-02 17:34:51 -08:00

worker

[BugFix] MLA + V1, illegal memory access and accuracy issues (#14253 )

2025-03-05 17:10:13 -08:00

__init__.py

[V1] AsyncLLM Implementation (#9826 )

2024-11-11 23:05:38 +00:00

kv_cache_interface.py

Update deprecated Python 3.8 typing (#13971 )

2025-03-02 17:34:51 -08:00

outputs.py

Update deprecated Python 3.8 typing (#13971 )

2025-03-02 17:34:51 -08:00

request.py

Update deprecated Python 3.8 typing (#13971 )

2025-03-02 17:34:51 -08:00

serial_utils.py

[V1] Use msgpack for core request serialization (#12918 )

2025-02-10 11:35:56 +08:00

utils.py

Update deprecated Python 3.8 typing (#13971 )

2025-03-02 17:34:51 -08:00