[Doc] Require GCC 13 for CUDA source builds (#60259)
Signed-off-by: Doug Smith <dosmith@redhat.com>
This commit is contained in:
@@ -1568,6 +1568,18 @@ if(VLLM_GPU_LANG STREQUAL "CUDA" OR VLLM_GPU_LANG STREQUAL "HIP")
|
||||
include(cmake/external_projects/triton_kernels.cmake)
|
||||
endif()
|
||||
|
||||
# DeepGEMM and DeepSelect host code uses C++20 <format>, which libstdc++
|
||||
# provides only from GCC 13 onward.
|
||||
if (VLLM_GPU_LANG STREQUAL "CUDA"
|
||||
AND CMAKE_CXX_COMPILER_ID STREQUAL "GNU"
|
||||
AND CMAKE_CXX_COMPILER_VERSION VERSION_LESS "13")
|
||||
message(FATAL_ERROR
|
||||
"GCC >= 13 is required to build vLLM with CUDA (found ${CMAKE_CXX_COMPILER_VERSION}). "
|
||||
"The DeepGEMM and DeepSelect dependencies use C++20 <format> in host code, "
|
||||
"which libstdc++ does not provide before GCC 13. "
|
||||
"See: https://github.com/vllm-project/vllm/issues/58158")
|
||||
endif()
|
||||
|
||||
# For CUDA we also build and ship some external projects.
|
||||
if (VLLM_GPU_LANG STREQUAL "CUDA")
|
||||
include(cmake/external_projects/deepgemm.cmake)
|
||||
|
||||
@@ -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:
|
||||
|
||||
|
||||
Reference in New Issue
Block a user