From bc13f7cf38b697b32ba8cc422a66c0b1007ba968 Mon Sep 17 00:00:00 2001 From: Zhou Taichang Date: Fri, 27 Feb 2026 16:06:30 +0800 Subject: [PATCH] [Doc] Update installation instructions for vllm 0.16.0 (#1505) Signed-off-by: tzhouam --- docs/getting_started/installation/gpu/cuda.inc.md | 15 +-------------- docs/getting_started/quickstart.md | 13 +------------ 2 files changed, 2 insertions(+), 26 deletions(-) diff --git a/docs/getting_started/installation/gpu/cuda.inc.md b/docs/getting_started/installation/gpu/cuda.inc.md index 5cfc725a7..c261e0d7a 100644 --- a/docs/getting_started/installation/gpu/cuda.inc.md +++ b/docs/getting_started/installation/gpu/cuda.inc.md @@ -20,20 +20,7 @@ Therefore, it is recommended to install vLLM and vLLM-Omni with a **fresh new** vLLM-Omni is built based on vLLM. Please install it with command below. ```bash -# vllm 0.16.0 is still under prerelease -uv pip install --prerelease=allow vllm --extra-index-url https://wheels.vllm.ai/2d5be1dd5ce2e44dfea53ea03ff61143da5137eb - -# vllm 0.16.0 may have some bugs for cuda 12.9, here is how we solve them: -export FLASHINFER_CUDA_TAG="$(python3 -c 'import torch; print((torch.version.cuda or "12.4").replace(".", ""))')" - -uv pip install --upgrade --force-reinstall \ - "flashinfer-python==0.6.3" \ - "flashinfer-cubin==0.6.3" \ - "flashinfer-jit-cache==0.6.3" \ - --extra-index-url "https://flashinfer.ai/whl/cu${FLASHINFER_CUDA_TAG}" - -uv pip install --upgrade --force-reinstall "nvidia-cublas-cu12==12.9.1.4" -uv pip install --upgrade --force-reinstall "numpy==2.2.6" +uv pip install vllm --torch-backend=auto ``` #### Installation of vLLM-Omni diff --git a/docs/getting_started/quickstart.md b/docs/getting_started/quickstart.md index 671cf1593..a3eece127 100644 --- a/docs/getting_started/quickstart.md +++ b/docs/getting_started/quickstart.md @@ -19,18 +19,7 @@ uv venv --python 3.12 --seed source .venv/bin/activate # On CUDA -# vllm 0.16.0 is still under prerelease -uv pip install --prerelease=allow vllm --extra-index-url https://wheels.vllm.ai/2d5be1dd5ce2e44dfea53ea03ff61143da5137eb -# vllm 0.16.0 may have some bugs for cuda 12.9, here is how we solve them: -export FLASHINFER_CUDA_TAG="$(python3 -c 'import torch; print((torch.version.cuda or "12.4").replace(".", ""))')" -uv pip install --upgrade --force-reinstall \ - "flashinfer-python==0.6.3" \ - "flashinfer-cubin==0.6.3" \ - "flashinfer-jit-cache==0.6.3" \ - --extra-index-url "https://flashinfer.ai/whl/cu${FLASHINFER_CUDA_TAG}" -uv pip install --upgrade --force-reinstall "nvidia-cublas-cu12==12.9.1.4" -uv pip install --upgrade --force-reinstall "numpy==2.2.6" - +uv pip install vllm==0.16.0 --torch-backend=auto # On ROCm uv pip install vllm==0.16.0 --extra-index-url https://wheels.vllm.ai/rocm/0.16.0/rocm700