biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Dev UX] Add auto-detection for VLLM_PRECOMPILED_WHEEL_VARIANT during install (#32948)

Browse Source 
Signed-off-by: mgoin <mgoin64@gmail.com>
Signed-off-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: Shengqi Chen <i@harrychen.xyz>
This commit is contained in:
Michael Goin
2026-01-23 22:15:17 -05:00
committed by GitHub
parent c0d820457a
commit d0cbac5827
2 changed files with 51 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
docs/getting_started/installation/gpu.cuda.inc.md
View File

@@ -118,7 +118,7 @@ There are more environment variables to control the behavior of Python-only buil
* `VLLM_PRECOMPILED_WHEEL_LOCATION`: specify the exact wheel URL or local file path of a pre-compiled wheel to use. All other logic to find the wheel will be skipped.
* `VLLM_PRECOMPILED_WHEEL_COMMIT`: override the commit hash to download the pre-compiled wheel. It can be `nightly` to use the last **already built** commit on the main branch.
* `VLLM_PRECOMPILED_WHEEL_VARIANT`: specify the variant subdirectory to use on the nightly index, e.g., `cu129`, `cpu`. If not specified, the CUDA variant with `VLLM_MAIN_CUDA_VERSION` will be tried, then fallback to the default variant on the remote index.
* `VLLM_PRECOMPILED_WHEEL_VARIANT`: specify the variant subdirectory to use on the nightly index, e.g., `cu129`, `cu130`, `cpu`. If not specified, the variant is auto-detected based on your system's CUDA version (from PyTorch or nvidia-smi). You can also set `VLLM_MAIN_CUDA_VERSION` to override auto-detection.
You can find more information about vLLM's wheels in [Install the latest code](#install-the-latest-code).