Files
vllm/docker
Tyler Michael Smithandkhluu ee20e1a8e8 [Build] Download CUDA 12.9 nvcc/ptxas for better codegen in Docker build
Use CUDA 12.9.86 compiler binaries (nvcc, ptxas, cicc) for better GPU
code generation while keeping CUDA 12.8 headers/libs for runtime
compatibility with PyTorch cu128 wheels.

Controlled by ARG NVCC_TOOLCHAIN_VERSION (default 12.9.86). Set to
empty string to disable.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
(cherry picked from commit fa2f0455aa6d4ad69c510eeb2516f026b26f795d)
2026-02-18 15:43:22 -08:00
..