- Add build-triton-kernels stage to fetch triton_kernels from Triton v3.6.0 - Install to site-packages for vLLM to find at runtime - Resolves: No module named 'triton_kernels.matmul_ogs' - Image tag: gh200-vllm-tfa:v0.19.0-tfa
VLLM images for GH200
Hosted here
docker login
# Alternative
# docker buildx build --platform linux/arm64 --memory=600g -t rajesh550/gh200-vllm:0.9.0.1 .
docker build --memory=450g --platform linux/arm64 -t rajesh550/gh200-vllm:0.11.1rc2 . 2>&1 | tee build.log
docker push rajesh550/gh200-vllm:0.11.1rc2