ImportError: /usr/local/app/.local/lib/python3.10/site-packages/flash_attn_2_cuda.cpython-310-x86_64
情况描述环境:linuxtransformers4.39.0tokenizers0.15.2torch2.1.2+cu121flash-attn2.3.3在使用vllm运行xverse/XVERSE-13B-256K时(代码如下):qwen_model=AutoModelForSequenceClassification.from_pretrained(args.pre_train,trust_r