modelscope-agent
modelscope-agent copied to clipboard
import flash_attn rotary fail
背景:在本地部署ModelScope-Agent-7B,机器为nvidia的A100,速度特别慢,chat一次平均耗时18秒 已经按照[https://modelscope.cn/models/iic/ModelScope-Agent-7B/summary的步骤安装了flash-attention==2.3.5、layer_norm、rotary-embedding-torch==0.5.3] 启动ModelScope-Agent-7B 还是报:Warning: import flash_attn rotary fail, please install FlashAttention rotary to get higher efficiency https://github.com/Dao-AILab/flash-attention/tree/main/csrc/rotary
帮忙看看呢
您好,最近modelscope-agent更新了版本,建议使用最新版本,关于本地部署的问题,可以参考这个下面这个关于无外网环境部署的方案 https://github.com/modelscope/modelscope-agent/pull/307/files