yuehuayingxueluo 86b63f720c [Inference]Adapted to the triton attn kernels (#5264) ... * adapted to the triton attn kernels * fix pad input * adapted to copy_kv_to_blocked_cache * fix ci test * update kv memcpy * remove print		2024-01-17 16:03:10 +08:00
..
layers	[Inference]Adapted to the triton attn kernels (#5264)	2024-01-17 16:03:10 +08:00
models	[Inference]Adapted to the triton attn kernels (#5264)	2024-01-17 16:03:10 +08:00
policy	Fixed a bug in the inference frame	2024-01-11 13:39:56 +00:00