Wang, Jian4 191b184341 LLM: Optimize cohere model (#10878) ... * use mlp and rms * optimize kv_cache * add fuse qkv * add flash attention and fp16 sdp * error fp8 sdp * fix optimized * fix style * update * add for pp		2024-05-07 10:19:50 +08:00
..
llm	LLM: Optimize cohere model (#10878)	2024-05-07 10:19:50 +08:00