search

Alpha-VLLM / LLaMA2-Accessory

An Open-source Toolkit for LLM Development
https://llama2-accessory.readthedocs.io/
Other
2.72k stars 176 forks source link

量化微调的时候如果用flashAttention则报错 #201

Open bibibabibo26 opened 6 months ago

bibibabibo26 commented 6 months ago

RuntimeError：FLashAttention only surpport fp16 and bf16 data type