For my local installs I usually use the command:
VLLM_USE_PRE_COMPILED=1 uv pip install -e .
VLLM_USE_PRECOMPILED=1so that I don’t have to compile the custom ops (your mileage may vary if you are using GPUs that vLLM doesn’t have precompiled binaries for)uv pipinstead ofpipbecause it’s blazing fast
-eso that changes to local files are used when running vLLM
With this setup I also have other packages (like transformers) locally installed with no issues.