Wang, Jian4 9bff84e6fd LLM: Convert draft_model kv_cache from bf16 to fp32 (#9964) ... * convert bf16 to fp32 * update * change when init * init first and cut off after * init and exchange * update python type * update * fix bug * update * update		2024-01-25 11:20:27 +08:00
..
llm	LLM: Convert draft_model kv_cache from bf16 to fp32 (#9964)	2024-01-25 11:20:27 +08:00