diff --git a/.github/workflows/release-docker-amd-nightly.yml b/.github/workflows/release-docker-amd-nightly.yml index f188fd03d..ea9949238 100644 --- a/.github/workflows/release-docker-amd-nightly.yml +++ b/.github/workflows/release-docker-amd-nightly.yml @@ -20,7 +20,7 @@ jobs: strategy: fail-fast: false matrix: - gpu_arch: ['gfx942', 'gfx942-rocm700', 'gfx950'] + gpu_arch: ['gfx942', 'gfx950'] build_type: ['all'] steps: - name: Checkout repository @@ -58,8 +58,6 @@ jobs: echo "Version: ${version}" if [ "${{ matrix.gpu_arch }}" = "gfx942" ]; then - rocm_tag="rocm630-mi30x" - elif [ "${{ matrix.gpu_arch }}" = "gfx942-rocm700" ]; then rocm_tag="rocm700-mi30x" elif [ "${{ matrix.gpu_arch }}" = "gfx950" ]; then rocm_tag="rocm700-mi35x" @@ -83,7 +81,7 @@ jobs: strategy: fail-fast: false matrix: - gpu_arch: ['gfx942', 'gfx942-rocm700'] + gpu_arch: ['gfx942'] build_type: ['all'] steps: - name: Checkout repository @@ -123,8 +121,6 @@ jobs: echo "Version: ${version}" if [ "${{ matrix.gpu_arch }}" = "gfx942" ]; then - rocm_tag="rocm630-mi30x" - elif [ "${{ matrix.gpu_arch }}" = "gfx942-rocm700" ]; then rocm_tag="rocm700-mi30x" else echo "Unsupported gfx arch" @@ -143,9 +139,7 @@ jobs: image="rocm/sgl-dev:${tag}-${{ env.DATE }}${tag_suffix}" # Determine target cache file name based on ROCm variant - if [[ "${rocm_tag}" == rocm630* ]]; then - final_path="/home/runner/sgl-data/docker/image.tar" - elif [[ "${rocm_tag}" == rocm700* ]]; then + if [[ "${rocm_tag}" == rocm700* ]]; then final_path="/home/runner/sgl-data/docker/image-700.tar" else echo "Unexpected ROCm tag: ${rocm_tag}" diff --git a/.github/workflows/release-docker-amd.yml b/.github/workflows/release-docker-amd.yml index a47104452..4c079c528 100644 --- a/.github/workflows/release-docker-amd.yml +++ b/.github/workflows/release-docker-amd.yml @@ -16,7 +16,7 @@ jobs: environment: 'prod' strategy: matrix: - gpu_arch: ['gfx942', 'gfx942-rocm700', 'gfx950'] + gpu_arch: ['gfx942', 'gfx950'] build_type: ['all'] steps: - name: Checkout repository @@ -56,8 +56,6 @@ jobs: echo "Version: ${version}" if [ "${{ matrix.gpu_arch }}" = "gfx942" ]; then - rocm_tag="rocm630-mi30x" - elif [ "${{ matrix.gpu_arch }}" = "gfx942-rocm700" ]; then rocm_tag="rocm700-mi30x" elif [ "${{ matrix.gpu_arch }}" = "gfx950" ]; then rocm_tag="rocm700-mi35x" diff --git a/docker/rocm.Dockerfile b/docker/rocm.Dockerfile index a6a44cef2..51f225b03 100644 --- a/docker/rocm.Dockerfile +++ b/docker/rocm.Dockerfile @@ -1,30 +1,19 @@ # Usage (to build SGLang ROCm docker image): -# docker build --build-arg SGL_BRANCH=v0.5.8 --build-arg GPU_ARCH=gfx942 -t v0.5.8-rocm630-mi30x -f rocm.Dockerfile . -# docker build --build-arg SGL_BRANCH=v0.5.8 --build-arg GPU_ARCH=gfx942-rocm700 -t v0.5.8-rocm700-mi30x -f rocm.Dockerfile . +# docker build --build-arg SGL_BRANCH=v0.5.8 --build-arg GPU_ARCH=gfx942 -t v0.5.8-rocm700-mi30x -f rocm.Dockerfile . # docker build --build-arg SGL_BRANCH=v0.5.8 --build-arg GPU_ARCH=gfx950 -t v0.5.8-rocm700-mi35x -f rocm.Dockerfile . + # Default base images -ARG BASE_IMAGE_942="rocm/sgl-dev:vllm20250114" -ARG BASE_IMAGE_942_ROCM700="rocm/sgl-dev:rocm7-vllm-20250904" +ARG BASE_IMAGE_942="rocm/sgl-dev:rocm7-vllm-20250904" ARG BASE_IMAGE_950="rocm/sgl-dev:rocm7-vllm-20250904" # This is necessary for scope purpose ARG GPU_ARCH=gfx950 # =============================== -# Base image 942 with rocm630 and args +# Base image 942 with rocm700 and args FROM $BASE_IMAGE_942 AS gfx942 ENV BUILD_VLLM="0" -ENV BUILD_TRITON="1" -ENV BUILD_LLVM="0" -ENV BUILD_AITER_ALL="1" -ENV BUILD_MOONCAKE="1" -ENV AITER_COMMIT="v0.1.4" - -# =============================== -# Base image 942 and args -FROM $BASE_IMAGE_942_ROCM700 AS gfx942-rocm700 -ENV BUILD_VLLM="0" ENV BUILD_TRITON="0" ENV BUILD_LLVM="0" ENV BUILD_AITER_ALL="1" @@ -109,7 +98,7 @@ RUN cd aiter \ fi # ----------------------- -# Triton +# Triton (TODO: remove this after Triton is no longer needed) RUN if [ "$BUILD_TRITON" = "1" ]; then \ pip uninstall -y triton \ && git clone ${TRITON_REPO} \ diff --git a/docs/developer_guide/setup_github_runner.md b/docs/developer_guide/setup_github_runner.md index 3ca9627ff..67d1b0be0 100644 --- a/docs/developer_guide/setup_github_runner.md +++ b/docs/developer_guide/setup_github_runner.md @@ -12,9 +12,9 @@ docker pull nvidia/cuda:12.9.1-devel-ubuntu22.04 # Nvidia docker run --shm-size 128g -it -v /tmp/huggingface:/hf_home --gpus all nvidia/cuda:12.9.1-devel-ubuntu22.04 /bin/bash # AMD -docker run --rm --device=/dev/kfd --device=/dev/dri --group-add video --shm-size 128g -it -v /tmp/huggingface:/hf_home lmsysorg/sglang:v0.5.0rc1-rocm630 /bin/bash +docker run --rm --device=/dev/kfd --device=/dev/dri --group-add video --shm-size 128g -it -v /tmp/huggingface:/hf_home lmsysorg/sglang:v0.5.8-rocm700-mi30x /bin/bash # AMD just the last 2 GPUs -docker run --rm --device=/dev/kfd --device=/dev/dri/renderD176 --device=/dev/dri/renderD184 --group-add video --shm-size 128g -it -v /tmp/huggingface:/hf_home lmsysorg/sglang:v0.5.0rc1-rocm630 /bin/bash +docker run --rm --device=/dev/kfd --device=/dev/dri/renderD176 --device=/dev/dri/renderD184 --group-add video --shm-size 128g -it -v /tmp/huggingface:/hf_home lmsysorg/sglang:v0.5.8-rocm700-mi30x /bin/bash ``` ### Step 2: Configure the runner by `config.sh` diff --git a/scripts/ci/amd/amd_ci_install_dependency.sh b/scripts/ci/amd/amd_ci_install_dependency.sh index 271adfaa7..73c1a8010 100755 --- a/scripts/ci/amd/amd_ci_install_dependency.sh +++ b/scripts/ci/amd/amd_ci_install_dependency.sh @@ -162,8 +162,8 @@ if [[ "${GPU_ARCH}" == "mi35x" ]]; then | head -n1 \ | sed 's/.*AITER_COMMIT="\([^"]*\)".*/\1/') else - echo "[CI-AITER-CHECK] Using gfx942-rocm700 block from Dockerfile..." - REPO_AITER_COMMIT=$(grep -F -A20 'FROM $BASE_IMAGE_942_ROCM700 AS gfx942-rocm700' docker/rocm.Dockerfile \ + echo "[CI-AITER-CHECK] Using gfx942 block from Dockerfile..." + REPO_AITER_COMMIT=$(grep -F -A20 'FROM $BASE_IMAGE_942 AS gfx942' docker/rocm.Dockerfile \ | grep 'AITER_COMMIT=' \ | head -n1 \ | sed 's/.*AITER_COMMIT="\([^"]*\)".*/\1/')