SONG Ge 13b0bc9075 [LLM] Add quantize_kv optimization for yuan2 model (#10243) ... * add initial quantize_kv support for yuan2 model * fix yuan2 quantize_kv generation * apply fp16 conv layer optimizations * disable mlp for quantize_kv		2024-02-29 16:33:26 +08:00
..
llm	[LLM] Add quantize_kv optimization for yuan2 model (#10243)	2024-02-29 16:33:26 +08:00
__init__.py	LLM: add first round files (#8225)	2023-05-25 11:29:18 +08:00