Thomas Parnell 6bd1dd9d26

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

2025-03-06 07:39:16 -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

Deprecate best_of Sampling Parameter in anticipation for vLLM V1 (#13997)

2025-03-05 20:22:43 +00:00

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