Woosuk KwonandGitHub 27208be66e [Kernel] Add back batch size 1536 and 3072 to MoE tuning (#5242)

2024-06-04 09:58:47 -07:00

..

benchmark_aqlm.py

[Core]refactor aqlm quant ops (#4351)

2024-04-25 15:03:56 -04:00

benchmark_marlin.py

Marlin 24 prefill performance improvement (about 25% better on average) (#4983)

2024-05-23 02:39:27 -04:00

benchmark_moe.py

[Kernel] Add back batch size 1536 and 3072 to MoE tuning (#5242)

2024-06-04 09:58:47 -07:00

benchmark_paged_attention.py

[Model] Support MAP-NEO model (#5081)

2024-05-30 19:24:41 -07:00

benchmark_rope.py

[Model] Support MAP-NEO model (#5081)

2024-05-30 19:24:41 -07:00

benchmark_shapes.py

Add marlin unit tests and marlin benchmark script (#4815)

2024-05-16 09:36:49 -04:00