Mingyi a523a3c13a Reduce hardcoded logic of kernel usage (#707)

2024-07-23 16:42:21 -07:00

..

quantization

refactor model loader [unreachable code]: initial refactor (#655)

2024-07-19 09:27:06 -07:00

context_flashattention_nopad.py

Remove cached triton launcher (#656)

2024-07-18 23:28:40 -07:00

extend_attention.py

Remove cached triton launcher (#656)

2024-07-18 23:28:40 -07:00

fused_moe.py

Format (#593)

2024-07-05 10:06:17 -07:00

linear.py

refactor model loader [unreachable code]: initial refactor (#655)

2024-07-19 09:27:06 -07:00

logits_processor.py

Support gpt-bigcode model class (#681)

2024-07-20 18:34:37 -07:00

radix_attention.py

Reduce hardcoded logic of kernel usage (#707)

2024-07-23 16:42:21 -07:00

token_attention.py

Remove cached triton launcher (#656)

2024-07-18 23:28:40 -07:00