Files
enginex-vllm-bi100-qwen36/qwen3_6_scripts/patch_ops.sh

11 lines
499 B
Bash
Raw Normal View History

pip install transformers==4.55.3 -i https://pypi.tuna.tsinghua.edu.cn/simple
cp -r ./qwen3_5 /usr/local/lib/python3.10/site-packages/transformers/models/
python3 ./patch_transformers_qwen3_5.py
cp ./mamba_cache.py /usr/local/corex/lib/python3/dist-packages/vllm/model_executor/models/
cp ./qwen3_5.py /usr/local/corex/lib/python3/dist-packages/vllm/model_executor/models/
python3 ./patch_vllm_qwen3_5.py
# 此步骤脚本四选一(默认 matmul+seq策略
python3 ./patch_xformers_sdpa_seq.py