obsidian_backup/InterestingStuffs/wsl ubuntu vllm.md

virtualenv vllm-env

source vllm-env/bin/activate deactivate

export http_proxy=http://172.28.21.225:7890 export https_proxy=http://172.28.21.225:7890

pip install -U vllm --pre --index-url https://pypi.org/simple --extra-index-url https://wheels.vllm.ai/nightly pip install git+https://github.com/huggingface/transformers.git

vllm serve zai-org/GLM-4.7-Flash --tensor-parallel-size 1 --speculative-config.method mtp --speculative-config.num_speculative_tokens 1 --tool-call-parser glm47 --reasoning-parser glm45 --enable-auto-tool-choice --served-model-name glm-4.7-flash