[Doc] Require GCC 13 for CUDA source builds (#60259)

Signed-off-by: Doug Smith <dosmith@redhat.com>
This commit is contained in:
Doug Smith
2026-10-08 09:43:39 -07:00
committed by GitHub
parent 8674a794c7
commit 242e4213fc
2 changed files with 14 additions and 7 deletions
@@ -140,13 +140,8 @@ You can find more information about vLLM's wheels in [Install the latest code](#
#### Full build (with compilation) {#full-build}
!!! note "Compiler requirement"
Building from source requires GCC/G++ ≥ 11.3. PyTorch's C++20 headers are
not compatible with GCC 10 or GCC < 11.3. On Ubuntu 22.04:
```bash
sudo apt-get install -y gcc-11 g++-11
sudo update-alternatives --install /usr/bin/gcc gcc /usr/bin/gcc-11 110 \
--slave /usr/bin/g++ g++ /usr/bin/g++-11
```
Building from source requires GCC/G++ ≥ 13 ([#58158](https://github.com/vllm-project/vllm/issues/58158)).
Ubuntu 24.04, the base of the default vLLM image, ships GCC 13 by default.
If you want to modify C++ or CUDA code, you'll need to build vLLM from source. This can take several minutes: