使用的镜像：image.sourcefind.cn:5000/dcu/admin/base/vllm:0.8.5-ubuntu22.04-dtk25.04.1-rc5-das1.6-py3.10-20250705 使用vllm推理时，运行命令python run_dpsk_ocr_image.py会报错，error: unsupported target: 'gfx906' 使用transformers推理也会报错，ImportError: cannot import name 'LlamaFlashAttention2' from 'transformers.models.llama.modeling_llama'