Mirror of the docs update that shipped with the v0.24.0 rebase (#4709): - quickstart + CUDA/ROCm install guides: vllm==0.24.0 -> 0.25.0 pins, git checkout tag, precompiled-wheel URL (asset verified on the v0.25.0 GitHub release), and docker image tags - ROCm wheel index suffix changed upstream: rocm722 -> rocm723 (wheels.vllm.ai/rocm/0.25.0/ serves only rocm723; ROCm 7.2.2 -> 7.2.3) - gpu.md: add 0.25.0 to the pre-built wheels list NPU docs still reference v0.24.0 Ascend images intentionally — those images are published separately by the NPU team. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
Installation
vLLM-Omni supports the following hardware platforms: