Ying Sheng fb9296f0ed Higher priority for user input of max_prefill_tokens & format (#540)

2024-06-12 21:48:40 -07:00

..

context_flashattention_nopad.py

add .isort.cfg (#378)

2024-04-22 22:38:09 +08:00

extend_attention.py

Improve logging & add logit cap (#471)

2024-05-24 03:48:53 -07:00

fused_moe.py

Higher priority for user input of max_prefill_tokens & format (#540)

2024-06-12 21:48:40 -07:00

logits_processor.py

Higher priority for user input of max_prefill_tokens & format (#540)

2024-06-12 21:48:40 -07:00

radix_attention.py

Higher priority for user input of max_prefill_tokens & format (#540)

2024-06-12 21:48:40 -07:00

token_attention.py

Support data parallelism (static) (#480)

2024-05-27 21:24:10 -07:00