A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 10, 05:15 UTC
Fix CUDA 13 wheel installation doc (#32276)
Signed-off-by: Dmitry Tokarev <dtokarev@nvidia.com>
Dmitry Tokarev committed
Jan 13, 2026 at 13:48 UTC
46f8c6b72513a7fd8983ac620da50cbbed116ca7
1 file changed
+2
-1
docs/getting_started/installation/gpu.cuda.inc.md
+2
-1
@@ -41,7 +41,8 @@ As of now, vLLM's binaries are compiled with CUDA 12.9 and public PyTorch releas
41
# Install vLLM with a specific CUDA version (e.g., 13.0).
42
export VLLM_VERSION=$(curl -s https://api.github.com/repos/vllm-project/vllm/releases/latest | jq -r .tag_name | sed 's/^v//')
43
export CUDA_VERSION=130 # or other
44
-uv pip install https://github.com/vllm-project/vllm/releases/download/v${VLLM_VERSION}/vllm-${VLLM_VERSION}+cu${CUDA_VERSION}-cp38-abi3-manylinux_2_31_x86_64.whl --extra-index-url https://download.pytorch.org/whl/cu${CUDA_VERSION}
44
+export CPU_ARCH=$(uname -m) # x86_64 or aarch64
45
+uv pip install https://github.com/vllm-project/vllm/releases/download/v${VLLM_VERSION}/vllm-${VLLM_VERSION}+cu${CUDA_VERSION}-cp38-abi3-manylinux_2_35_${CPU_ARCH}.whl --extra-index-url https://download.pytorch.org/whl/cu${CUDA_VERSION}
46
```
47
48
#### Install the latest code