forked from Karylab-cklius/vllm
Use CUDA 12.9.86 compiler toolchain (nvcc, ptxas, cicc) for better GPU code generation while keeping CUDA 12.8 headers/libs for runtime compatibility with PyTorch cu128 wheels. nvcc is replaced (not just ptxas/cicc) so that setup.py's get_nvcc_cuda_version() reports 12.9, which is required for FlashMLA registration. PyTorch's CMake nvcc-vs-header version check is patched to a warning in base (for extensions-build), csrc-build, and build stages (re-applied after torch pip reinstall overwrites cmake files). Controlled by ARG MIN_NVCC_TOOLCHAIN_VERSION (default 12.9.86): - Skipped if system nvcc is already >= the specified version - Set to empty string to disable entirely - Archive integrity verified via SHA256 checksums from NVIDIA's redistrib manifest Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> Signed-off-by: Tyler Michael Smith <tlrmchlsmth@gmail.com>
102 lines
2.3 KiB
JSON
102 lines
2.3 KiB
JSON
{
|
|
"_comment": "Auto-generated from Dockerfile ARGs. Do not edit manually. Run: python tools/generate_versions_json.py",
|
|
"variable": {
|
|
"CUDA_VERSION": {
|
|
"default": "12.8.1"
|
|
},
|
|
"PYTHON_VERSION": {
|
|
"default": "3.12"
|
|
},
|
|
"BUILD_BASE_IMAGE": {
|
|
"default": "nvidia/cuda:12.8.1-devel-ubuntu20.04"
|
|
},
|
|
"FINAL_BASE_IMAGE": {
|
|
"default": "nvidia/cuda:12.8.1-base-ubuntu22.04"
|
|
},
|
|
"GET_PIP_URL": {
|
|
"default": "https://bootstrap.pypa.io/get-pip.py"
|
|
},
|
|
"PYTORCH_CUDA_INDEX_BASE_URL": {
|
|
"default": "https://download.pytorch.org/whl"
|
|
},
|
|
"PIP_KEYRING_PROVIDER": {
|
|
"default": "disabled"
|
|
},
|
|
"UV_KEYRING_PROVIDER": {
|
|
"default": "disabled"
|
|
},
|
|
"INSTALL_KV_CONNECTORS": {
|
|
"default": "false"
|
|
},
|
|
"TORCH_CUDA_ARCH_LIST": {
|
|
"default": "7.0 7.5 8.0 8.9 9.0 10.0 12.0"
|
|
},
|
|
"MIN_NVCC_TOOLCHAIN_VERSION": {
|
|
"default": "12.9.86"
|
|
},
|
|
"NVCC_TOOLCHAIN_SHA256_X86_64": {
|
|
"default": "7a1a5b652e5ef85c82b721d10672fc9a2dbaab44e9bd3c65a69517bf53998c35"
|
|
},
|
|
"NVCC_TOOLCHAIN_SHA256_AARCH64": {
|
|
"default": "2432ef8a7c12d0a9ce3332a8af42b123c07f256390b3390802b1b2c6254c6c74"
|
|
},
|
|
"MAX_JOBS": {
|
|
"default": "2"
|
|
},
|
|
"NVCC_THREADS": {
|
|
"default": "8"
|
|
},
|
|
"SCCACHE_BUCKET_NAME": {
|
|
"default": "vllm-build-sccache"
|
|
},
|
|
"SCCACHE_REGION_NAME": {
|
|
"default": "us-west-2"
|
|
},
|
|
"SCCACHE_S3_NO_CREDENTIALS": {
|
|
"default": "0"
|
|
},
|
|
"vllm_target_device": {
|
|
"default": "cuda"
|
|
},
|
|
"DEEPGEMM_GIT_REF": {
|
|
"default": "477618cd51baffca09c4b0b87e97c03fe827ef03"
|
|
},
|
|
"PPLX_COMMIT_HASH": {
|
|
"default": "12cecfd"
|
|
},
|
|
"DEEPEP_COMMIT_HASH": {
|
|
"default": "73b6ea4"
|
|
},
|
|
"GIT_REPO_CHECK": {
|
|
"default": "0"
|
|
},
|
|
"VLLM_MAX_SIZE_MB": {
|
|
"default": "500"
|
|
},
|
|
"RUN_WHEEL_CHECK": {
|
|
"default": "true"
|
|
},
|
|
"FLASHINFER_VERSION": {
|
|
"default": "0.6.3"
|
|
},
|
|
"GDRCOPY_CUDA_VERSION": {
|
|
"default": "12.8"
|
|
},
|
|
"GDRCOPY_OS_VERSION": {
|
|
"default": "Ubuntu22_04"
|
|
},
|
|
"BITSANDBYTES_VERSION_X86": {
|
|
"default": "0.46.1"
|
|
},
|
|
"BITSANDBYTES_VERSION_ARM64": {
|
|
"default": "0.42.0"
|
|
},
|
|
"TIMM_VERSION": {
|
|
"default": ">=1.0.17"
|
|
},
|
|
"RUNAI_MODEL_STREAMER_VERSION": {
|
|
"default": ">=0.15.3"
|
|
}
|
|
}
|
|
}
|