--extra-index-url https://download.pytorch.org/whl/cu130
# vLLM's PyPI wheel is built against CUDA 12 (libcudart.so.12) and won't load
# on a cu130 host. Pull the cu130-flavoured wheel from vLLM's per-tag index
# instead — the cublas13 case in install.sh adds --index-strategy=unsafe-best-match
# so uv consults this index alongside PyPI.
--extra-index-url https://wheels.vllm.ai/0.24.0/cu130
# VERSION COUPLING: darwin/Apple-Silicon builds use vllm-metal (see install.sh),
# which pins this exact vLLM version. Bumping vllm here means coordinating with a
# vllm-metal release that supports the new version, or macOS/Metal builds break.
vllm==0.24.0