Yuanheng Zhao 3da9993b0d [Kernel/Fix] Revise flash attention triton kernel API and add benchmark (#5301) ... * fix decoding kernel pytest * revise and add triton context attn benchmark		2024-01-23 17:16:02 +08:00
..
layers	[Kernel/Fix] Revise flash attention triton kernel API and add benchmark (#5301)	2024-01-23 17:16:02 +08:00
models	[inference] Adapted to Rotary Embedding and RMS Norm (#5283)	2024-01-22 10:55:34 +08:00
policy	[inference] Adapted to Rotary Embedding and RMS Norm (#5283)	2024-01-22 10:55:34 +08:00