minke.yu/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 12 Packages Projects Releases Wiki Activity

[AMD] [Docker] Upgrade Python 3.12 + torch 2.11 + triton 3.7 in ROCm 7.2.4 (#30984)

Browse Source 
Co-authored-by: Chen <bingxche@amd.com>
This commit is contained in:
chuyeh
2026-08-19 18:18:31 -07:00
committed by GitHub
co-authored by Chen
parent ab203663c4
commit c7478228dd
9 changed files with 428 additions and 132 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.github/workflows/pr-test-amd-extra.yml
+15 -3
View File
@@ -37,18 +37,24 @@ on:
- mi300
- mi325
rocm_version:
description: 'ROCm container variant (rocm720 = ROCm 7.2.0, the PR default; rocm700 = ROCm 7.0.0)'
description: 'ROCm container variant (ROCm 7.2.0 by default)'
required: false
type: choice
default: rocm720
options:
- rocm720
- rocm724
- rocm700
aiter_ref:
description: 'Override AITER commit (optional, leave empty to use Dockerfile default)'
required: false
type: string
default: ''
amd_ci_image:
description: 'Override AMD CI Docker image (optional, e.g. rocm/sgl-dev:tag)'
required: false
type: string
default: ''
continue_on_error:
description: 'Continue on error (do not fail the workflow on test failures)'
required: false
@@ -67,7 +73,7 @@ on:
type: string
default: mi300
rocm_version:
description: 'ROCm container variant (rocm720 = ROCm 7.2.0, the PR default; rocm700 = ROCm 7.0.0)'
description: 'ROCm container variant (ROCm 7.2.0 by default)'
required: false
type: string
default: rocm720
@@ -76,6 +82,11 @@ on:
required: false
type: string
default: ''
amd_ci_image:
description: 'Override AMD CI Docker image (optional, e.g. rocm/sgl-dev:tag)'
required: false
type: string
default: ''
continue_on_error:
description: 'Continue on error (do not fail the workflow on test failures)'
required: false
@@ -84,6 +95,7 @@ on:
env:
AITER_COMMIT_OVERRIDE: ${{ inputs.aiter_ref }}
AMD_CI_IMAGE: ${{ inputs.amd_ci_image }}
DOCKERHUB_AMD_USERNAME: ${{ secrets.DOCKERHUB_AMD_USERNAME }}
DOCKERHUB_AMD_TOKEN: ${{ secrets.DOCKERHUB_AMD_TOKEN }}
@@ -145,7 +157,7 @@ jobs:
- name: Start CI container
# `inputs` is empty on pull_request events, so fall back explicitly to
# the ROCm 7.2 PR default. Reusable callers can still request ROCm 7.0.
# the ROCm 7.2 PR default. Reusable callers can request another variant.
run: bash scripts/ci/amd/amd_ci_start_container.sh --rocm-version ${{ inputs.rocm_version || 'rocm720' }}
env:
GITHUB_WORKSPACE: ${{ github.workspace }}
.github/workflows/pr-test-amd-rocm720.yml
+46 -20
View File
@@ -16,6 +16,14 @@ on:
- "docker/rocm.Dockerfile"
workflow_dispatch:
inputs:
rocm_version:
description: 'ROCm image version'
required: false
type: choice
default: rocm720
options:
- rocm720
- rocm724
target_stage_select:
description: "Select a stage to run from dropdown (leave empty for auto-detect)"
required: false
@@ -57,6 +65,11 @@ on:
required: false
type: string
default: ''
amd_ci_image:
description: 'Override AMD CI Docker image (optional, e.g. rocm/sgl-dev:tag)'
required: false
type: string
default: ''
continue_on_error:
description: 'Continue on error (do not fail the workflow on test failures)'
required: false
@@ -77,6 +90,11 @@ on:
default: false
workflow_call:
inputs:
rocm_version:
description: 'ROCm image version'
required: false
type: string
default: rocm720
ref:
description: 'Git ref (branch, tag, or SHA) to test. If not provided, uses the default branch.'
required: false
@@ -97,6 +115,11 @@ on:
required: false
type: string
default: ''
amd_ci_image:
description: 'Override AMD CI Docker image (optional, e.g. rocm/sgl-dev:tag)'
required: false
type: string
default: ''
continue_on_error:
description: 'Continue on error (do not fail the workflow on test failures)'
required: false
@@ -116,6 +139,8 @@ permissions:
env:
AITER_COMMIT_OVERRIDE: ${{ inputs.aiter_ref }}
AMD_CI_IMAGE: ${{ inputs.amd_ci_image }}
ROCM_VERSION: ${{ inputs.rocm_version || 'rocm720' }}
DOCKERHUB_AMD_USERNAME: ${{ secrets.DOCKERHUB_AMD_USERNAME }}
DOCKERHUB_AMD_TOKEN: ${{ secrets.DOCKERHUB_AMD_TOKEN }}
@@ -225,8 +250,9 @@ jobs:
with:
ref: ${{ inputs.pr_head_sha || inputs.ref || '' }}
runner_arch: ${{ inputs.runner_arch || 'mi300' }}
rocm_version: rocm720
rocm_version: ${{ inputs.rocm_version || 'rocm720' }}
aiter_ref: ${{ inputs.aiter_ref }}
amd_ci_image: ${{ inputs.amd_ci_image }}
continue_on_error: true
secrets: inherit
@@ -255,7 +281,7 @@ jobs:
run: bash scripts/ci/amd/ensure_vram_clear.sh rocm
- name: Start CI container
run: bash scripts/ci/amd/amd_ci_start_container.sh --rocm-version rocm720
run: bash scripts/ci/amd/amd_ci_start_container.sh --rocm-version "$ROCM_VERSION"
env:
GITHUB_WORKSPACE: ${{ github.workspace }}
@@ -313,7 +339,7 @@ jobs:
run: bash scripts/ci/amd/ensure_vram_clear.sh rocm
- name: Start CI container
run: bash scripts/ci/amd/amd_ci_start_container.sh --rocm-version rocm720
run: bash scripts/ci/amd/amd_ci_start_container.sh --rocm-version "$ROCM_VERSION"
env:
GITHUB_WORKSPACE: ${{ github.workspace }}
@@ -354,7 +380,7 @@ jobs:
run: bash scripts/ci/amd/ensure_vram_clear.sh rocm
- name: Start CI container
run: bash scripts/ci/amd/amd_ci_start_container.sh --rocm-version rocm720
run: bash scripts/ci/amd/amd_ci_start_container.sh --rocm-version "$ROCM_VERSION"
env:
GITHUB_WORKSPACE: ${{ github.workspace }}
@@ -391,7 +417,7 @@ jobs:
run: bash scripts/ci/amd/ensure_vram_clear.sh rocm
- name: Start CI container
run: bash scripts/ci/amd/amd_ci_start_container.sh --rocm-version rocm720
run: bash scripts/ci/amd/amd_ci_start_container.sh --rocm-version "$ROCM_VERSION"
env:
GITHUB_WORKSPACE: ${{ github.workspace }}
@@ -428,7 +454,7 @@ jobs:
run: bash scripts/ci/amd/ensure_vram_clear.sh rocm
- name: Start CI container
run: bash scripts/ci/amd/amd_ci_start_container.sh --rocm-version rocm720
run: bash scripts/ci/amd/amd_ci_start_container.sh --rocm-version "$ROCM_VERSION"
env:
GITHUB_WORKSPACE: ${{ github.workspace }}
@@ -496,7 +522,7 @@ jobs:
run: bash scripts/ci/amd/ensure_vram_clear.sh rocm
- name: Start CI container
run: bash scripts/ci/amd/amd_ci_start_container.sh --rocm-version rocm720
run: bash scripts/ci/amd/amd_ci_start_container.sh --rocm-version "$ROCM_VERSION"
env:
GITHUB_WORKSPACE: ${{ github.workspace }}
@@ -532,7 +558,7 @@ jobs:
run: bash scripts/ci/amd/ensure_vram_clear.sh rocm
- name: Start CI container
run: bash scripts/ci/amd/amd_ci_start_container.sh --rocm-version rocm720
run: bash scripts/ci/amd/amd_ci_start_container.sh --rocm-version "$ROCM_VERSION"
env:
GITHUB_WORKSPACE: ${{ github.workspace }}
@@ -571,7 +597,7 @@ jobs:
run: bash scripts/ci/amd/ensure_vram_clear.sh rocm
- name: Start CI container
run: bash scripts/ci/amd/amd_ci_start_container.sh --rocm-version rocm720
run: bash scripts/ci/amd/amd_ci_start_container.sh --rocm-version "$ROCM_VERSION"
env:
GITHUB_WORKSPACE: ${{ github.workspace }}
@@ -612,7 +638,7 @@ jobs:
run: bash scripts/ci/amd/ensure_vram_clear.sh rocm
- name: Start CI container
run: bash scripts/ci/amd/amd_ci_start_container.sh --rocm-version rocm720
run: bash scripts/ci/amd/amd_ci_start_container.sh --rocm-version "$ROCM_VERSION"
env:
GITHUB_WORKSPACE: ${{ github.workspace }}
@@ -653,7 +679,7 @@ jobs:
run: bash scripts/ci/amd/ensure_vram_clear.sh rocm
- name: Start CI container
run: bash scripts/ci/amd/amd_ci_start_container.sh --rocm-version rocm720
run: bash scripts/ci/amd/amd_ci_start_container.sh --rocm-version "$ROCM_VERSION"
env:
GITHUB_WORKSPACE: ${{ github.workspace }}
@@ -702,7 +728,7 @@ jobs:
pattern: wheel-python3.10-cuda12.9
- name: Start CI container
run: bash scripts/ci/amd/amd_ci_start_container.sh --rocm-version rocm720
run: bash scripts/ci/amd/amd_ci_start_container.sh --rocm-version "$ROCM_VERSION"
env:
GITHUB_WORKSPACE: ${{ github.workspace }}
@@ -833,7 +859,7 @@ jobs:
pattern: wheel-python3.10-cuda12.9
- name: Start CI container
run: bash scripts/ci/amd/amd_ci_start_container.sh --rocm-version rocm720
run: bash scripts/ci/amd/amd_ci_start_container.sh --rocm-version "$ROCM_VERSION"
env:
GITHUB_WORKSPACE: ${{ github.workspace }}
@@ -963,7 +989,7 @@ jobs:
pattern: wheel-python3.10-cuda12.9
- name: Start CI container
run: bash scripts/ci/amd/amd_ci_start_container.sh --rocm-version rocm720
run: bash scripts/ci/amd/amd_ci_start_container.sh --rocm-version "$ROCM_VERSION"
env:
GITHUB_WORKSPACE: ${{ github.workspace }}
@@ -1040,7 +1066,7 @@ jobs:
run: bash scripts/ci/amd/ensure_vram_clear.sh rocm
- name: Start CI container
run: bash scripts/ci/amd/amd_ci_start_container.sh --rocm-version rocm720
run: bash scripts/ci/amd/amd_ci_start_container.sh --rocm-version "$ROCM_VERSION"
env:
GITHUB_WORKSPACE: ${{ github.workspace }}
@@ -1099,7 +1125,7 @@ jobs:
run: bash scripts/ci/amd/ensure_vram_clear.sh rocm
- name: Start CI container
run: bash scripts/ci/amd/amd_ci_start_container.sh --rocm-version rocm720
run: bash scripts/ci/amd/amd_ci_start_container.sh --rocm-version "$ROCM_VERSION"
env:
GITHUB_WORKSPACE: ${{ github.workspace }}
@@ -1145,7 +1171,7 @@ jobs:
run: bash scripts/ci/amd/ensure_vram_clear.sh rocm
- name: Start CI container
run: bash scripts/ci/amd/amd_ci_start_container.sh --rocm-version rocm720
run: bash scripts/ci/amd/amd_ci_start_container.sh --rocm-version "$ROCM_VERSION"
env:
GITHUB_WORKSPACE: ${{ github.workspace }}
@@ -1189,7 +1215,7 @@ jobs:
- name: Setup docker (ROCm 7.2)
run: |
touch github_summary.md
bash scripts/ci/amd/amd_ci_start_container.sh --rocm-version rocm720
bash scripts/ci/amd/amd_ci_start_container.sh --rocm-version "$ROCM_VERSION"
env:
GITHUB_WORKSPACE: ${{ github.workspace }}
ENABLE_CACHE_HOST: "1"
@@ -1243,7 +1269,7 @@ jobs:
- name: Setup docker (ROCm 7.2)
run: |
touch github_summary.md
bash scripts/ci/amd/amd_ci_start_container.sh --rocm-version rocm720
bash scripts/ci/amd/amd_ci_start_container.sh --rocm-version "$ROCM_VERSION"
env:
GITHUB_WORKSPACE: ${{ github.workspace }}
ENABLE_CACHE_HOST: "1"
@@ -1336,7 +1362,7 @@ jobs:
echo "=== Host RDMA Check Complete ==="
- name: Start Special Container
run: bash scripts/ci/amd/amd_ci_start_container_disagg.sh --rocm-version rocm720
run: bash scripts/ci/amd/amd_ci_start_container_disagg.sh --rocm-version "$ROCM_VERSION"
env:
GITHUB_WORKSPACE: ${{ github.workspace }}
.github/workflows/release-docker-amd-rocm720-nightly.yml
+18 -3
View File
@@ -10,6 +10,17 @@ on:
options:
- 'all'
- publish
gpu_arch:
description: 'Select which ROCm 7.2 GPU arch to build'
required: false
type: choice
default: 'all'
options:
- 'all'
- gfx942-rocm724
- gfx950-rocm724
- gfx942-rocm720
- gfx950-rocm720
schedule:
- cron: '0 12 * * *'
@@ -29,7 +40,7 @@ jobs:
strategy:
fail-fast: false
matrix:
gpu_arch: ['gfx942-rocm720', 'gfx950-rocm720']
gpu_arch: ${{ fromJson((github.event_name == 'workflow_dispatch' && inputs.gpu_arch != 'all' && inputs.gpu_arch != '') && format('["{0}"]', inputs.gpu_arch) || '["gfx942-rocm720", "gfx950-rocm720", "gfx942-rocm724", "gfx950-rocm724"]') }}
build_type: ['all']
steps:
- name: Checkout repository
@@ -81,7 +92,11 @@ jobs:
echo "Version: ${version}"
echo "Pretend version: ${pretend_version}"
if [ "${{ matrix.gpu_arch }}" = "gfx942-rocm720" ]; then
if [ "${{ matrix.gpu_arch }}" = "gfx942-rocm724" ]; then
rocm_tag="rocm724-mi30x"
elif [ "${{ matrix.gpu_arch }}" = "gfx950-rocm724" ]; then
rocm_tag="rocm724-mi35x"
elif [ "${{ matrix.gpu_arch }}" = "gfx942-rocm720" ]; then
rocm_tag="rocm720-mi30x"
elif [ "${{ matrix.gpu_arch }}" = "gfx950-rocm720" ]; then
rocm_tag="rocm720-mi35x"
@@ -141,7 +156,7 @@ jobs:
strategy:
fail-fast: false
matrix:
gpu_arch: ['gfx942-rocm720', 'gfx950-rocm720']
gpu_arch: ${{ fromJson((github.event_name == 'workflow_dispatch' && inputs.gpu_arch != 'all' && inputs.gpu_arch != '') && format('["{0}"]', inputs.gpu_arch) || '["gfx942-rocm720", "gfx950-rocm720", "gfx942-rocm724", "gfx950-rocm724"]') }}
steps:
- name: Download image tag artifact
uses: actions/download-artifact@v4
.github/workflows/release-docker-amd.yml
+17 -4
View File
@@ -8,6 +8,16 @@ on:
version:
description: 'Version to build (without v prefix, e.g., 0.5.7)'
required: true
rocm_version:
description: 'ROCm version to build'
required: false
type: choice
default: 'all'
options:
- 'all'
- rocm724
- rocm720
- rocm700
jobs:
publish:
@@ -15,8 +25,11 @@ jobs:
runs-on: amd-docker-scale
environment: 'prod'
strategy:
# Six flavors publish independently: a failure in one must not cancel the
# others mid-push and leave the release tag with a partial image set.
fail-fast: false
matrix:
rocm_version: ['rocm700', 'rocm720']
rocm_version: ${{ fromJson((github.event_name == 'workflow_dispatch' && inputs.rocm_version != 'all' && inputs.rocm_version != '') && format('["{0}"]', inputs.rocm_version) || '["rocm700", "rocm720", "rocm724"]') }}
gpu_arch: ['gfx942', 'gfx950']
build_type: ['all']
steps:
@@ -66,12 +79,12 @@ jobs:
echo "Unsupported gfx arch"
exit 1
fi
elif [ "${{ matrix.rocm_version }}" = "rocm720" ]; then
elif [ "${{ matrix.rocm_version }}" = "rocm720" ] || [ "${{ matrix.rocm_version }}" = "rocm724" ]; then
gpu_arch_suffix="-${{ matrix.rocm_version }}"
if [ "${{ matrix.gpu_arch }}" = "gfx942" ]; then
rocm_tag="rocm720-mi30x"
rocm_tag="${{ matrix.rocm_version }}-mi30x"
elif [ "${{ matrix.gpu_arch }}" = "gfx950" ]; then
rocm_tag="rocm720-mi35x"
rocm_tag="${{ matrix.rocm_version }}-mi35x"
else
echo "Unsupported gfx arch"
exit 1
docker/rocm.Dockerfile
+199 -48
View File
@@ -1,8 +1,15 @@
# Usage (to build SGLang ROCm docker image):
# docker build --build-arg SGL_BRANCH=v0.5.10.post1 --build-arg GPU_ARCH=gfx942 -t v0.5.10.post1-rocm700-mi30x -f rocm.Dockerfile .
# docker build --build-arg SGL_BRANCH=v0.5.10.post1 --build-arg GPU_ARCH=gfx942-rocm720 -t v0.5.10.post1-rocm720-mi30x -f rocm.Dockerfile .
# docker build --build-arg SGL_BRANCH=v0.5.10.post1 --build-arg GPU_ARCH=gfx942-rocm724 -t v0.5.10.post1-rocm724-mi30x -f rocm.Dockerfile .
# docker build --build-arg SGL_BRANCH=v0.5.10.post1 --build-arg GPU_ARCH=gfx950 -t v0.5.10.post1-rocm700-mi35x -f rocm.Dockerfile .
# docker build --build-arg SGL_BRANCH=v0.5.10.post1 --build-arg GPU_ARCH=gfx950-rocm720 -t v0.5.10.post1-rocm720-mi35x -f rocm.Dockerfile .
# docker build --build-arg SGL_BRANCH=v0.5.10.post1 --build-arg GPU_ARCH=gfx950-rocm724 -t v0.5.10.post1-rocm724-mi35x -f rocm.Dockerfile .
#
# Flavor notes:
# GPU_ARCH=*-rocm724 is built on a Python 3.12 base and upgrades the stack to
# torch 2.11 (+torchvision 0.26 / torchaudio 2.11) and Triton 3.7.
# The ROCm 7.2.0 flavors remain on Python 3.10 and torch 2.9.1.
# Usage (to build SGLang ROCm + Mori docker image):
# remove --build-arg NIC_BACKEND=ainic since new MoRI JIT will do NIC auto detection on target
@@ -23,8 +30,10 @@
# Default base images
ARG BASE_IMAGE_942="rocm/sgl-dev:rocm7-vllm-20250904"
ARG BASE_IMAGE_942_ROCM720="rocm/pytorch:rocm7.2_ubuntu22.04_py3.10_pytorch_release_2.9.1"
ARG BASE_IMAGE_942_ROCM724="rocm/pytorch:rocm7.2.4_ubuntu24.04_py3.12_pytorch_release_2.10.0"
ARG BASE_IMAGE_950="rocm/sgl-dev:rocm7-vllm-20250904"
ARG BASE_IMAGE_950_ROCM720="rocm/pytorch:rocm7.2_ubuntu22.04_py3.10_pytorch_release_2.9.1"
ARG BASE_IMAGE_950_ROCM724="rocm/pytorch:rocm7.2.4_ubuntu24.04_py3.12_pytorch_release_2.10.0"
# This is necessary for scope purpose
ARG GPU_ARCH=gfx950
@@ -49,6 +58,30 @@ ENV BUILD_AITER_ALL="1"
ENV BUILD_MOONCAKE="1"
ENV AITER_COMMIT_DEFAULT="d9e5ef7ce08ee7045d583aed768cff41aa9210fe"
# ===============================
# Base image 942 with rocm724 and args (Python 3.12 + torch 2.11)
FROM $BASE_IMAGE_942_ROCM724 AS gfx942-rocm724
ENV BUILD_VLLM="0"
ENV BUILD_TRITON="1"
ENV BUILD_LLVM="0"
ENV BUILD_AITER_ALL="1"
ENV BUILD_MOONCAKE="1"
ENV AITER_COMMIT_DEFAULT="d9e5ef7ce08ee7045d583aed768cff41aa9210fe"
# Pin the ROCm torch stack for every pip invocation in this flavor. The file is
# filled in after the torch 2.11 upgrade below; it must already exist (empty is
# valid) because pip reads PIP_CONSTRAINT from the first pip call onwards.
# Deliberately still set in the shipped image, not just during the build: a later
# `pip install` that resolves torch would otherwise pull the PyPI CUDA build over
# this ROCm one, and the constraint turns that into a resolution error instead.
# It names only torch / torchvision / torchaudio, so nothing else is constrained.
ENV PIP_CONSTRAINT="/etc/sglang/constraints/torch-rocm.txt"
RUN mkdir -p /etc/sglang/constraints && : > /etc/sglang/constraints/torch-rocm.txt
# Work around ROCM-21485: the CUDA/ROCm IPC path leaks GPU memory (a freed IPC
# block is not returned to the driver). Legacy IPC mode releases it. Verified on
# ROCm 7.2.1 and 7.2.4; scoped to this flavor so rocm700 / rocm720 keep current
# IPC behavior.
ENV HSA_ENABLE_IPC_MODE_LEGACY=1
# ===============================
# Base image 950 and args
FROM $BASE_IMAGE_950 AS gfx950
@@ -69,6 +102,30 @@ ENV BUILD_AITER_ALL="1"
ENV BUILD_MOONCAKE="1"
ENV AITER_COMMIT_DEFAULT="d9e5ef7ce08ee7045d583aed768cff41aa9210fe"
# ===============================
# Base image 950 with rocm724 and args (Python 3.12 + torch 2.11)
FROM $BASE_IMAGE_950_ROCM724 AS gfx950-rocm724
ENV BUILD_VLLM="0"
ENV BUILD_TRITON="1"
ENV BUILD_LLVM="0"
ENV BUILD_AITER_ALL="1"
ENV BUILD_MOONCAKE="1"
ENV AITER_COMMIT_DEFAULT="d9e5ef7ce08ee7045d583aed768cff41aa9210fe"
# Pin the ROCm torch stack for every pip invocation in this flavor. The file is
# filled in after the torch 2.11 upgrade below; it must already exist (empty is
# valid) because pip reads PIP_CONSTRAINT from the first pip call onwards.
# Deliberately still set in the shipped image, not just during the build: a later
# `pip install` that resolves torch would otherwise pull the PyPI CUDA build over
# this ROCm one, and the constraint turns that into a resolution error instead.
# It names only torch / torchvision / torchaudio, so nothing else is constrained.
ENV PIP_CONSTRAINT="/etc/sglang/constraints/torch-rocm.txt"
RUN mkdir -p /etc/sglang/constraints && : > /etc/sglang/constraints/torch-rocm.txt
# Work around ROCM-21485: the CUDA/ROCm IPC path leaks GPU memory (a freed IPC
# block is not returned to the driver). Legacy IPC mode releases it. Verified on
# ROCm 7.2.1 and 7.2.4; scoped to this flavor so rocm700 / rocm720 keep current
# IPC behavior.
ENV HSA_ENABLE_IPC_MODE_LEGACY=1
# Local source stage: with BRANCH_TYPE=local the build context is copied here and
# used instead of git clone (mirrors docker/Dockerfile's local_src stage).
FROM scratch AS local_src
@@ -80,6 +137,11 @@ FROM ${GPU_ARCH}
# This is necessary for scope purpose, again
ARG GPU_ARCH=gfx950
# ARG is build-time only. Stamp the stage name (gfx950-rocm724, gfx942, ...)
# so CI can read which AITER_COMMIT_DEFAULT block to use instead of guessing
# from torch or HIP — 720 may also ship torch 2.11 later, and both 7.2 flavors
# report HIP 7.2*.
ENV GPU_ARCH=${GPU_ARCH}
ENV GPU_ARCH_LIST=${GPU_ARCH%-*}
ENV PYTORCH_ROCM_ARCH=gfx942;gfx950
@@ -91,6 +153,22 @@ ARG BRANCH_TYPE=remote
# Version override for setuptools_scm (used in nightly builds)
ARG SETUPTOOLS_SCM_PRETEND_VERSION=""
# ROCm 7.2 Triton (BUILD_TRITON=1 stages only). Both wheels are the same
# upstream revision, triton-lang/triton@89002410. AITER only requires
# triton>=3.6.0 and treats the base image as the owner of the version, so the
# choice is ours; bump these together after checking the index.
ARG TRITON_INDEX_URL="https://pypi.amd.com/triton/release/rocm-7.2.0/simple/"
ARG TRITON_VERSION="3.7.0+amd.rocm7.2.0.git89002410"
ARG TRITON_KERNELS_VERSION="1.0.0+amd.rocm7.2.0.git89002410"
# ROCm 7.2.4 torch upgrade pins (Python 3.12). Torch 2.11 for ROCm 7.2 is only
# published on the PyTorch Foundation index; AMD's repo.radeon.com wheels top
# out at torch 2.10.
ARG TORCH_ROCM_INDEX_URL="https://download.pytorch.org/whl/rocm7.2"
ARG TORCH_ROCM_VERSION="2.11.0+rocm7.2"
ARG TORCHVISION_ROCM_VERSION="0.26.0+rocm7.2"
ARG TORCHAUDIO_ROCM_VERSION="2.11.0+rocm7.2"
ARG AITER_REPO="https://github.com/ROCm/aiter.git"
ARG AITER_COMMIT=""
ENV AITER_COMMIT="${AITER_COMMIT:-${AITER_COMMIT_DEFAULT}}"
@@ -131,14 +209,16 @@ ARG UBUNTU_CODENAME=jammy
# Optional Ubuntu mirror override + apt hardening.
# - UBUNTU_MIRROR is empty by default (no behaviour change for local builds).
# When set (typically in CI), all http://*archive.ubuntu.com and
# http://*security.ubuntu.com entries in /etc/apt/sources.list are rewritten
# to point at the given base URL, e.g.
# http://*security.ubuntu.com entries in every /etc/apt source file are
# rewritten to point at the given base URL, e.g.
# --build-arg UBUNTU_MIRROR=https://archive.ubuntu.com
# --build-arg UBUNTU_MIRROR=https://tw.archive.ubuntu.com
# --build-arg UBUNTU_MIRROR=http://internal-cache.example.com
# This mirrors the pattern already used in docker/Dockerfile (NVIDIA) and
# docker/npu.Dockerfile, and lets CI runners that cannot reach Canonical's
# port-80 mirror IPs still complete `apt-get update`.
# port-80 mirror IPs still complete `apt-get update`. Every file, not just
# sources.list: the noble base used by rocm724 keeps its URIs in the deb822
# /etc/apt/sources.list.d/ubuntu.sources instead.
# - The 80-net-hardening apt config adds retries + per-request timeout so that
# transient mirror flakes don't immediately fail a build (apt's default is 0
# retries).
@@ -146,21 +226,40 @@ ARG UBUNTU_MIRROR=
USER root
RUN if [ -n "$UBUNTU_MIRROR" ]; then \
sed -i "s|http://[^[:space:]/]*archive.ubuntu.com|$UBUNTU_MIRROR|g" /etc/apt/sources.list && \
sed -i "s|http://[^[:space:]/]*security.ubuntu.com|$UBUNTU_MIRROR|g" /etc/apt/sources.list; \
find /etc/apt -type f \( -name '*.list' -o -name '*.sources' \) \
-exec sed -i \
-e "s|http://[^[:space:]/]*archive.ubuntu.com|$UBUNTU_MIRROR|g" \
-e "s|http://[^[:space:]/]*security.ubuntu.com|$UBUNTU_MIRROR|g" \
{} + ; \
fi && \
printf 'Acquire::Retries "5";\nAcquire::http::Timeout "30";\nAcquire::https::Timeout "30";\n' \
> /etc/apt/apt.conf.d/80-net-hardening
# Fix hipDeviceGetName returning empty string in ROCm 7.0 docker images.
# The ROCm 7.0 base image is missing libdrm-amdgpu-common which provides the
# amdgpu.ids device-ID-to-marketing-name mapping file.
# ROCm 7.2 base images already ship these packages, so this step is skipped.
# Fix hipDeviceGetName returning empty / generic names.
# amdgpu.ids maps PCI IDs to marketing names. The ROCm 7.0 base is missing it.
# The 7.2.0 base was built with amdgpu-install and already has it. The 7.2.4
# ubuntu24.04 base installs the `rocm` apt metapackage and does not; noble's
# distro table has MI300 (74A*) but no MI355X (75A3), so gfx950-rocm724 would
# otherwise report "AMD Radeon Graphics" and miss every name-keyed config.
# See https://github.com/ROCm/ROCm/issues/5992
RUN set -eux; \
case "${GPU_ARCH}" in \
*rocm724*) \
echo "ROCm 7.2.4 (GPU_ARCH=${GPU_ARCH}): installing libdrm-amdgpu from graphics/7.2.4 noble"; \
curl -fsSL https://repo.radeon.com/rocm/rocm.gpg.key \
| gpg --dearmor -o /etc/apt/keyrings/amdgpu-graphics.gpg \
&& echo 'deb [arch=amd64,i386 signed-by=/etc/apt/keyrings/amdgpu-graphics.gpg] https://repo.radeon.com/graphics/7.2.4/ubuntu noble main' \
> /etc/apt/sources.list.d/amdgpu-graphics.list \
&& apt-get update \
&& apt-get install -y --no-install-recommends \
libdrm-amdgpu-common \
libdrm-amdgpu-amdgpu1 \
libdrm2-amdgpu \
&& rm -rf /var/lib/apt/lists/* \
&& cp /opt/amdgpu/share/libdrm/amdgpu.ids /usr/share/libdrm/amdgpu.ids; \
;; \
*rocm720*) \
echo "ROCm 7.2 (GPU_ARCH=${GPU_ARCH}): libdrm-amdgpu packages already present, skipping"; \
echo "ROCm 7.2.0 (GPU_ARCH=${GPU_ARCH}): libdrm-amdgpu packages already present, skipping"; \
;; \
*) \
echo "ROCm 7.0 (GPU_ARCH=${GPU_ARCH}): installing libdrm-amdgpu packages"; \
@@ -187,7 +286,7 @@ RUN apt-get purge -y sccache; python -m pip uninstall -y sccache; rm -f "$(which
# The ROCm 7.2 base image (rocm/pytorch) does not pre-install this package.
RUN set -eux; \
case "${GPU_ARCH}" in \
*rocm720*) \
*rocm720*|*rocm724*) \
echo "ROCm 7.2 flavor detected from GPU_ARCH=${GPU_ARCH}"; \
cd /opt/rocm/share/amd_smi \
&& python3 -m pip install --no-cache-dir . \
@@ -197,6 +296,33 @@ RUN set -eux; \
;; \
esac
# -----------------------
# ROCm 7.2.4: upgrade torch 2.10 -> 2.11 (+ vision/audio), which pulls triton-rocm 3.6.0.
# Done here, before AITER / sgl-kernel, so those extensions build against torch 2.11's ABI.
RUN case "${GPU_ARCH}" in \
*-rocm724) \
python3 -m pip install --no-cache-dir --index-url "${TORCH_ROCM_INDEX_URL}" \
"torch==${TORCH_ROCM_VERSION}" \
"torchvision==${TORCHVISION_ROCM_VERSION}" \
"torchaudio==${TORCHAUDIO_ROCM_VERSION}" \
;; \
*) \
echo "Not a ROCm 7.2.4 flavor (GPU_ARCH=${GPU_ARCH}), keep base torch/triton"; \
;; \
esac
# Populate the PIP_CONSTRAINT file, which only the rocm724 stages define, so that
# resolving AITER and SGLang dependencies cannot replace the torch stack above.
# Triton is left out: the BUILD_TRITON step installs it later.
RUN case "${GPU_ARCH}" in \
*-rocm724) \
python3 -m pip freeze \
| grep -E '^(torch|torchvision|torchaudio)(==| @ )' \
> /etc/sglang/constraints/torch-rocm.txt \
&& cat /etc/sglang/constraints/torch-rocm.txt \
;; \
esac
WORKDIR /sgl-workspace
# -----------------------
@@ -220,7 +346,7 @@ RUN if [ "$BUILD_LLVM" = "1" ]; then \
ENV SETUPTOOLS_SCM_PRETEND_VERSION=
# Compile AITER against the base image's Triton; the Triton step at the end of
# this file swaps in AITER's own pin afterwards.
# this file installs the pinned one afterwards.
ENV AITER_USE_SYSTEM_TRITON=1
RUN pip uninstall -y aiter
# Use `checkout -f` so the smudge-filter-induced "dirty" working tree from
@@ -248,6 +374,28 @@ RUN cd aiter \
fi \
&& echo "export PYTHONPATH=/sgl-workspace/aiter:\${PYTHONPATH}" >> /etc/bash.bashrc
# torch 2.11 Dynamo may pass a base torch.Stream; drop after ROCm/aiter#4817.
RUN python3 <<'PY'
from pathlib import Path
p = Path("/sgl-workspace/aiter/csrc/cpp_itfs/torch_utils.py")
s = p.read_text()
old = """ elif isinstance(arg, torch.cuda.Stream):
c_args.append(ctypes.cast(arg.cuda_stream, ctypes.c_void_p))
"""
new = """ elif isinstance(arg, torch.Stream):
handle = getattr(arg, "cuda_stream", None)
if handle is None:
handle = torch.cuda.Stream(
stream_id=arg.stream_id,
device_index=arg.device_index,
device_type=arg.device_type,
).cuda_stream
c_args.append(ctypes.cast(handle, ctypes.c_void_p))
"""
if old in s:
p.write_text(s.replace(old, new))
PY
# -----------------------
# Build Mooncake
ENV PATH=$PATH:/usr/local/go/bin
@@ -319,14 +467,30 @@ RUN if [ "$BRANCH_TYPE" = "local" ]; then \
&& AMDGPU_TARGET=$GPU_ARCH_LIST python setup_rocm.py install \
&& cd ../../../.. \
&& rm -rf python/pyproject.toml && mv python/pyproject_other.toml python/pyproject.toml \
# srt_hip pins compressed-tensors==0.15.0, which requires torch<2.11 and so
# cannot be satisfied on the ROCm 7.2.4 torch 2.11 stack. The *_rocm724 extras
# carry a 0.16.0 pin instead; all other flavors keep the extras they used before.
&& case "${GPU_ARCH}" in \
*-rocm724) srt_extras="srt_hip_rocm724,diffusion_hip"; all_extras="all_hip_rocm724" ;; \
*) srt_extras="srt_hip,diffusion_hip"; all_extras="all_hip" ;; \
esac \
&& if [ "$BUILD_TYPE" = "srt" ]; then \
export SETUPTOOLS_SCM_PRETEND_VERSION="${SETUPTOOLS_SCM_PRETEND_VERSION}" && python -m pip --no-cache-dir install -e "python[srt_hip,diffusion_hip]"; \
export SETUPTOOLS_SCM_PRETEND_VERSION="${SETUPTOOLS_SCM_PRETEND_VERSION}" && python -m pip --no-cache-dir install -e "python[${srt_extras}]"; \
else \
export SETUPTOOLS_SCM_PRETEND_VERSION="${SETUPTOOLS_SCM_PRETEND_VERSION}" && python -m pip --no-cache-dir install -e "python[all_hip]"; \
export SETUPTOOLS_SCM_PRETEND_VERSION="${SETUPTOOLS_SCM_PRETEND_VERSION}" && python -m pip --no-cache-dir install -e "python[${all_extras}]"; \
fi
RUN python -m pip cache purge
RUN if [ "${GPU_ARCH##*-}" = "rocm724" ]; then \
python3 -m pip check \
&& python3 -c "import torch, torchaudio, torchvision, triton; expected={'torch':'2.11.','torchaudio':'2.11.','torchvision':'0.26.'}; actual={'torch':torch.__version__,'torchaudio':torchaudio.__version__,'torchvision':torchvision.__version__,'triton':triton.__version__}; assert torch.version.hip, actual; assert all(actual[name].startswith(version) for name, version in expected.items()), actual; print('Validated ROCm stack:', actual, 'HIP', torch.version.hip)" \
&& if pip list --format=freeze | grep -Eq '^nvidia-.*-cu[0-9]+'; then \
echo "ERROR: NVIDIA CUDA runtime packages were installed into the ROCm image"; \
exit 1; \
fi; \
fi
# Copy config files to support MI300X in virtualized environments (MI300X_VF). Symlinks will not be created in image build.
RUN find /sgl-workspace/sglang/python/sglang/srt/layers/quantization/configs/ \
/sgl-workspace/sglang/python/sglang/srt/layers/moe/fused_moe_triton/configs/ \
@@ -536,6 +700,13 @@ RUN /bin/bash -lc 'set -euo pipefail; \
apt-get update && apt-get install -y --no-install-recommends \
build-essential autoconf automake libtool pkg-config git \
libibverbs-dev librdmacm-dev rdma-core && rm -rf /var/lib/apt/lists/*; \
# Mooncake's dependencies.sh apt-installs Ubuntu's libabsl-dev (20220623 on
# the noble base used by rocm724). NIXL's meson then finds absl_base but no
# absl_log and refuses to fall back to its bundled Abseil -- "that would
# result in a mix of Abseil versions at runtime" -- so nixl fails at metadata
# generation. Drop just the -dev package (headers and pkg-config files); the
# runtime library that already-built components link against stays in place.
case "${GPU_ARCH}" in *-rocm724) apt-get remove -y libabsl-dev ;; esac; \
pip install --no-cache-dir meson ninja pybind11 meson-python patchelf pyyaml; \
git clone --depth=1 -b "${UCX_BRANCH}" "${UCX_REPO}" /sgl-workspace/ucx; \
cd /sgl-workspace/ucx && ./autogen.sh && mkdir build && cd build && \
@@ -624,50 +795,30 @@ RUN cd /tmp/whl \
;; \
esac
# -----------------------
# Hot patch: transformers dynamic_module_utils symlink bug (v5.12.1).
# _compute_local_source_files_hash calls Path(...).resolve() on custom-code
# module files, following the HF-cache snapshots/<hash>/x.py -> blobs/<blob>
# symlink. trust_remote_code models whose custom code uses relative imports
# (e.g. Kimi-K2.6's kimi_k25_vision_processing.py: `from .media_utils import`)
# then crash with FileNotFoundError: .../blobs/<name>.py at processor init.
# Mirrors upstream transformers PR #46618 (merged, not yet released): drop the
# .resolve() on the module file and its relative-import sources so the snapshot
# .py names (not the blob targets) are used. Self-skips once transformers ships
# the fix; fails the build loudly if the pattern is present but unpatched.
RUN python3 - <<'PY'
import pathlib
import transformers.dynamic_module_utils as m
MARKS = ["Path(resolved_module_file).resolve()", "Path(source_file).resolve()"]
path = pathlib.Path(m.__file__)
src = path.read_text()
if not any(mark in src for mark in MARKS):
print("transformers dynamic_module_utils already fixed; no patch needed")
else:
patched = (
src.replace("Path(resolved_module_file).resolve()", "Path(resolved_module_file)")
.replace("Path(source_file).resolve()", "Path(source_file)")
)
assert patched != src, "FATAL: transformers symlink patch matched nothing"
path.write_text(patched)
print("patched transformers dynamic_module_utils.py (symlink hash fix)")
PY
# transformers 5.12.1: don't follow HF-cache symlinks when hashing custom modules
# (transformers#46618, not yet released).
RUN python3 -c "from pathlib import Path; import transformers.dynamic_module_utils as m; p=Path(m.__file__); t=p.read_text(); p.write_text(t.replace('Path(resolved_module_file).resolve()','Path(resolved_module_file)').replace('Path(source_file).resolve()','Path(source_file)'))"
# -----------------------
# Install the Triton AITER pins, replacing the base image's. No version check
# on purpose: the pin is AITER's to move, and its installer enforces a floor.
# Install AMD's ROCm Triton, replacing the base image's. The local version is
# part of the pin: `==3.7.0` alone would accept any revision the index later
# publishes under that number, and pip would choose between them by lexical
# order of the git hash rather than by date.
#
# Keep this last. Base ROCm Torch pins triton==3.5.1 and the torch patch above
# is what drops that pin, so installing Triton any earlier lets the next pip
# install pull CUDA torch instead. The hip check below is the tripwire.
# torch 2.11 names this `triton-rocm`; uninstall it so the pin is the only Triton.
RUN if [ "$BUILD_TRITON" = "1" ]; then \
cd /sgl-workspace/aiter \
&& test -f .github/scripts/install_triton.sh \
&& PIP_NO_CACHE_DIR=1 bash .github/scripts/install_triton.sh \
pip uninstall -y triton-rocm || true \
&& PIP_NO_CACHE_DIR=1 pip install --extra-index-url ${TRITON_INDEX_URL} \
"triton==${TRITON_VERSION}" "triton-kernels==${TRITON_KERNELS_VERSION}" \
&& python3 -c "import torch; from importlib.metadata import version; v = version('triton'); k = version('triton-kernels'); assert torch.version.hip is not None, torch.__version__; print(f'[Triton] ROCm Torch {torch.__version__}, Triton {v}, triton-kernels {k}')"; \
fi
# torch 2.11 still Requires-Dist: triton-rocm after the swap above.
RUN case "${GPU_ARCH}" in *-rocm724) python3 -c "import pathlib,re,importlib.metadata as m; p=pathlib.Path(m.distribution('torch')._path)/'METADATA'; v=m.version('triton'); t,n=re.subn(r'^Requires-Dist: (?:triton|triton-rocm)==[^ ;]+', 'Requires-Dist: triton=='+v, p.read_text(), count=1, flags=re.M); assert n==1, n; p.write_text(t)" ;; esac
# -----------------------
# Performance environment variable.
python/pyproject_other.toml
+17
View File
@@ -107,6 +107,10 @@ tracing = [
# HIP (Heterogeneous-computing Interface for Portability) for AMD
# => base docker rocm/vllm-dev:20250114, not from public vllm whl
#
# srt_hip_rocm724 below is the torch 2.11 variant of this list and differs only
# in its compressed-tensors and torch pins. A dependency added here has to be
# added there too; nothing enforces that.
srt_hip = [
# Pin to 0.15.0: 0.16.0 needs torch>=2.10 (incompatible with ROCm torch
# 2.9.1). An open-ended `<0.16.0` made pip backtrack into an unbuildable
@@ -118,6 +122,17 @@ srt_hip = [
"wave-lang==3.8.2",
]
# Kept in step with srt_hip above by hand; only the two pins below differ.
srt_hip_rocm724 = [
# ROCm 7.2.4 uses torch 2.11. compressed-tensors 0.15.0 requires
# torch<2.11, while 0.16.0 supports torch>=2.10.
"compressed-tensors==0.16.0",
"petit_kernel==0.0.2",
"sglang[runtime_common]",
"torch==2.11.0",
"wave-lang==3.8.2",
]
diffusion_hip = [
"cache-dit==1.3.0",
"peft>=0.18.0,<0.19.0", # Pin to <0.19.0 due to torchao incompatibility
@@ -189,11 +204,13 @@ test = [
]
all_hip = ["sglang[diffusion_hip]", "sglang[srt_hip]", "sglang[tracing]"]
all_hip_rocm724 = ["sglang[diffusion_hip]", "sglang[srt_hip_rocm724]", "sglang[tracing]"]
all_hpu = ["sglang[srt_hpu]"]
all_musa = ["sglang[diffusion_musa]", "sglang[srt_musa]"]
all_mps = ["sglang[diffusion_mps]", "sglang[srt_mps]"]
dev_hip = ["sglang[all_hip]", "sglang[test]"]
dev_hip_rocm724 = ["sglang[all_hip_rocm724]", "sglang[test]"]
dev_hpu = ["sglang[all_hpu]", "sglang[test]"]
dev_musa = ["sglang[all_musa]", "sglang[test]"]
dev_mps = ["sglang[all_mps]", "sglang[test]"]
scripts/ci/amd/amd_ci_install_dependency.sh
+88 -38
View File
@@ -30,7 +30,6 @@ EXTRAS="dev_hip,tracing"
if [ -n "$OPTIONAL_DEPS" ]; then
EXTRAS="dev_hip,tracing,${OPTIONAL_DEPS}"
fi
echo "Installing python extras: [${EXTRAS}]"
# Host names look like: linux-mi35x-gpu-1-xxxxx-runner-zzzzz
if [[ "${HOSTNAME_VALUE}" =~ ^linux-(mi[0-9]+[a-z]*)-gpu-[0-9]+ ]]; then
@@ -40,7 +39,56 @@ else
echo "Warning: could not parse GPU architecture from '${HOSTNAME_VALUE}', defaulting to ${GPU_ARCH}"
fi
# Identify the Dockerfile stage that built this image. Both the python extras
# below and the AITER pin lookup further down need the flavor, and they have to
# agree, so detect it once here.
#
# Prefer GPU_ARCH stamped into the image (gfx950-rocm724, gfx942, ...).
# Images built before that ENV existed: 724 stages already set
# PIP_CONSTRAINT and HSA_ENABLE_IPC_MODE_LEGACY; remaining HIP 7.2* is
# 720; else 7.0. Do not key off torch 2.11 — 720 may ship that later.
IMAGE_TORCH_VERSION=$(docker exec ci_sglang python3 -c 'import torch; print(torch.__version__)')
IMAGE_HIP_VERSION=$(docker exec ci_sglang python3 -c 'import torch; print(torch.version.hip or "")')
IMAGE_GPU_ARCH=$(docker exec ci_sglang printenv GPU_ARCH 2>/dev/null || true)
if [[ "${IMAGE_GPU_ARCH}" =~ ^(gfx942|gfx950)(-rocm720|-rocm724)?$ ]]; then
echo "[CI-IMAGE] Image GPU_ARCH=${IMAGE_GPU_ARCH}"
case "${IMAGE_GPU_ARCH}" in
*-rocm724) IMAGE_BASE_ARG_SUFFIX="_ROCM724"; IMAGE_STAGE_SUFFIX="-rocm724" ;;
*-rocm720) IMAGE_BASE_ARG_SUFFIX="_ROCM720"; IMAGE_STAGE_SUFFIX="-rocm720" ;;
*) IMAGE_BASE_ARG_SUFFIX=""; IMAGE_STAGE_SUFFIX="" ;;
esac
IMAGE_GFX="${IMAGE_GPU_ARCH%-*}"
else
IMAGE_PIP_CONSTRAINT=$(docker exec ci_sglang printenv PIP_CONSTRAINT 2>/dev/null || true)
IMAGE_HSA_LEGACY=$(docker exec ci_sglang printenv HSA_ENABLE_IPC_MODE_LEGACY 2>/dev/null || true)
if [[ -n "${IMAGE_PIP_CONSTRAINT}" || "${IMAGE_HSA_LEGACY}" == "1" ]]; then
IMAGE_BASE_ARG_SUFFIX="_ROCM724"
IMAGE_STAGE_SUFFIX="-rocm724"
elif [[ "${IMAGE_HIP_VERSION}" == 7.2* ]]; then
IMAGE_BASE_ARG_SUFFIX="_ROCM720"
IMAGE_STAGE_SUFFIX="-rocm720"
else
IMAGE_BASE_ARG_SUFFIX=""
IMAGE_STAGE_SUFFIX=""
fi
if [[ "${GPU_ARCH}" == "mi35x" ]]; then
IMAGE_GFX="gfx950"
else
IMAGE_GFX="gfx942"
fi
echo "[CI-IMAGE] Image has no GPU_ARCH stamp; inferred ${IMAGE_GFX}${IMAGE_STAGE_SUFFIX} (PIP_CONSTRAINT='${IMAGE_PIP_CONSTRAINT}', HSA_ENABLE_IPC_MODE_LEGACY='${IMAGE_HSA_LEGACY}', HIP=${IMAGE_HIP_VERSION})"
unset IMAGE_PIP_CONSTRAINT IMAGE_HSA_LEGACY
fi
unset IMAGE_GPU_ARCH
# Install the required dependencies in CI.
# ROCm 7.2.4 images ship torch 2.11, which srt_hip cannot satisfy (it pins
# compressed-tensors 0.15.0, requiring torch<2.11). Select the rocm724 extras.
if [[ "${IMAGE_STAGE_SUFFIX}" == "-rocm724" ]]; then
EXTRAS="${EXTRAS/dev_hip/dev_hip_rocm724}"
fi
echo "Image torch ${IMAGE_TORCH_VERSION}, HIP ${IMAGE_HIP_VERSION}; installing python extras: [${EXTRAS}]"
# Fix permissions on pip cache, ignore errors from concurrent access or missing temp files
docker exec ci_sglang chown -R root:root /sgl-data/pip-cache 2>/dev/null || true
docker exec ci_sglang pip install --cache-dir=/sgl-data/pip-cache --upgrade pip
@@ -221,6 +269,8 @@ if docker exec ci_sglang test -d /sgl-workspace/mori; then
cd /sgl-workspace/mori
git checkout '${MORI_COMMIT}'
git submodule update --init --recursive
apt-get update
apt-get install -y --no-install-recommends libgrpc++-dev 2>/dev/null || true
python3 setup.py develop
python3 -c 'import os, torch; print(os.path.join(os.path.dirname(torch.__file__), \"lib\"))' > /etc/ld.so.conf.d/torch.conf
ldconfig
@@ -248,35 +298,23 @@ DOCKERFILE="docker/rocm.Dockerfile"
GPU_ARCH="${GPU_ARCH:-mi30x}"
echo "[CI-AITER-CHECK] Runner GPU_ARCH=${GPU_ARCH}"
# ROCm 7.0 keeps the Triton its base image ships; later ROCm images run on the
# Triton AITER pins, so a rebuilt AITER has to bring its own along.
IMAGE_HIP_VERSION=$(docker exec ci_sglang python3 -c 'import torch; print(torch.version.hip or "")')
case "${IMAGE_HIP_VERSION}" in
7.0*) INSTALL_AITER_TRITON="false" ;;
7.*) INSTALL_AITER_TRITON="true" ;;
*)
echo "[CI-AITER-CHECK] ERROR: Unsupported or empty HIP version: '${IMAGE_HIP_VERSION}'"
exit 1
;;
esac
echo "[CI-AITER-CHECK] Container HIP=${IMAGE_HIP_VERSION}, install AITER's Triton on rebuild=${INSTALL_AITER_TRITON}"
# Image owns Triton (pinned in docker/rocm.Dockerfile). Rebuild AITER against it.
#############################################
# 1. Extract AITER_COMMIT from correct Dockerfile block
# 1. Extract AITER_COMMIT from the Dockerfile stage that built this image, as
# identified near the top of this script.
#############################################
if [[ "${GPU_ARCH}" == "mi35x" ]]; then
echo "[CI-AITER-CHECK] Using gfx950 block from Dockerfile..."
REPO_AITER_COMMIT=$(grep -F -A20 'FROM $BASE_IMAGE_950 AS gfx950' docker/rocm.Dockerfile \
| grep 'AITER_COMMIT_DEFAULT=' \
| head -n1 \
| sed 's/.*AITER_COMMIT_DEFAULT="\([^"]*\)".*/\1/')
if [[ "${IMAGE_GFX}" == "gfx950" ]]; then
_from_line="FROM \$BASE_IMAGE_950${IMAGE_BASE_ARG_SUFFIX} AS gfx950${IMAGE_STAGE_SUFFIX}"
else
echo "[CI-AITER-CHECK] Using gfx942 block from Dockerfile..."
REPO_AITER_COMMIT=$(grep -F -A20 'FROM $BASE_IMAGE_942 AS gfx942' docker/rocm.Dockerfile \
| grep 'AITER_COMMIT_DEFAULT=' \
| head -n1 \
| sed 's/.*AITER_COMMIT_DEFAULT="\([^"]*\)".*/\1/')
_from_line="FROM \$BASE_IMAGE_942${IMAGE_BASE_ARG_SUFFIX} AS gfx942${IMAGE_STAGE_SUFFIX}"
fi
echo "[CI-AITER-CHECK] Using ${_from_line} from Dockerfile..."
REPO_AITER_COMMIT=$(grep -F -A20 "${_from_line}" docker/rocm.Dockerfile \
| grep 'AITER_COMMIT_DEFAULT=' \
| head -n1 \
| sed 's/.*AITER_COMMIT_DEFAULT="\([^"]*\)".*/\1/')
unset _from_line
if [[ -z "${REPO_AITER_COMMIT}" ]]; then
@@ -344,6 +382,30 @@ if [[ "${NEED_REBUILD}" == "true" ]]; then
pip install -r requirements.txt
"
# Re-apply the Dockerfile torch.Stream patch after re-clone (ROCm/aiter#4817).
if [[ "${IMAGE_STAGE_SUFFIX}" == "-rocm724" ]]; then
docker exec -i ci_sglang python3 - <<'PY'
from pathlib import Path
p = Path("/sgl-workspace/aiter/csrc/cpp_itfs/torch_utils.py")
s = p.read_text()
old = """ elif isinstance(arg, torch.cuda.Stream):
c_args.append(ctypes.cast(arg.cuda_stream, ctypes.c_void_p))
"""
new = """ elif isinstance(arg, torch.Stream):
handle = getattr(arg, "cuda_stream", None)
if handle is None:
handle = torch.cuda.Stream(
stream_id=arg.stream_id,
device_index=arg.device_index,
device_type=arg.device_type,
).cuda_stream
c_args.append(ctypes.cast(handle, ctypes.c_void_p))
"""
if old in s:
p.write_text(s.replace(old, new))
PY
fi
if [[ "${GPU_ARCH}" == "mi35x" ]]; then
GPU_ARCH_LIST="gfx950"
else
@@ -351,19 +413,7 @@ if [[ "${NEED_REBUILD}" == "true" ]]; then
fi
echo "[CI-AITER-CHECK] GPU_ARCH_LIST=${GPU_ARCH_LIST}"
# Run the installer here rather than letting setup.py do it: setup.py
# swallows its errors, and the AITER_USE_SYSTEM_TRITON=1 below then keeps
# whatever Triton is already installed. Doing it up front fails closed.
if [[ "${INSTALL_AITER_TRITON}" == "true" ]]; then
docker exec ci_sglang bash -c "
set -euo pipefail
cd /sgl-workspace/aiter
test -f .github/scripts/install_triton.sh
bash .github/scripts/install_triton.sh
"
fi
# build AITER
# The image already has the Dockerfile-pinned Triton; compile against it.
docker exec ci_sglang bash -c "
cd /sgl-workspace/aiter && \
AITER_USE_SYSTEM_TRITON=1 GPU_ARCHS=${GPU_ARCH_LIST} python3 setup.py develop
scripts/ci/amd/amd_ci_start_container.sh
+2 -2
View File
@@ -28,7 +28,7 @@ LOCAL_DOCKER_REGISTRY="10.44.14.109:5000"
# Parse command line arguments
MI30X_BASE_TAG="${DEFAULT_MI30X_BASE_TAG}"
MI35X_BASE_TAG="${DEFAULT_MI35X_BASE_TAG}"
CUSTOM_IMAGE=""
CUSTOM_IMAGE="${AMD_CI_IMAGE:-}"
BUILD_FROM_DOCKERFILE=""
GPU_ARCH_BUILD=""
@@ -50,7 +50,7 @@ while [[ $# -gt 0 ]]; do
echo "Options:"
echo " --mi30x-base-tag TAG Override MI30x base image tag"
echo " --mi35x-base-tag TAG Override MI35x base image tag"
echo " --custom-image IMAGE Use a specific Docker image directly"
echo " --custom-image IMAGE Use a specific Docker image directly (or set AMD_CI_IMAGE)"
echo " --build-from-dockerfile Build image from docker/rocm.Dockerfile"
echo " --gpu-arch ARCH GPU architecture for Dockerfile build (e.g., gfx950-rocm720)"
echo " --rocm-version VERSION Override ROCm version for image lookup (e.g., rocm720)"
scripts/ci/amd/amd_ci_start_container_disagg.sh
+26 -14
View File
@@ -28,11 +28,13 @@ LOCAL_DOCKER_REGISTRY="10.44.14.109:5000"
# Parse command line arguments
MI30X_BASE_TAG="${DEFAULT_MI30X_BASE_TAG}"
MI35X_BASE_TAG="${DEFAULT_MI35X_BASE_TAG}"
CUSTOM_IMAGE="${AMD_CI_IMAGE:-}"
while [[ $# -gt 0 ]]; do
case $1 in
--mi30x-base-tag) MI30X_BASE_TAG="$2"; shift 2;;
--mi35x-base-tag) MI35X_BASE_TAG="$2"; shift 2;;
--custom-image) CUSTOM_IMAGE="$2"; shift 2;;
--rocm-version)
ROCM_VERSION="$2"
MI30X_BASE_TAG="${SGLANG_VERSION}-${ROCM_VERSION}-mi30x"
@@ -40,7 +42,7 @@ while [[ $# -gt 0 ]]; do
echo "Using ROCm version override: ${ROCM_VERSION}"
shift 2;;
-h|--help)
echo "Usage: $0 [--mi30x-base-tag TAG] [--mi35x-base-tag TAG] [--rocm-version VERSION]"
echo "Usage: $0 [--mi30x-base-tag TAG] [--mi35x-base-tag TAG] [--custom-image IMAGE] [--rocm-version VERSION]"
exit 0
;;
*) echo "Unknown option $1"; exit 1;;
@@ -212,20 +214,30 @@ find_latest_image() {
esac
}
# Pull and run the latest image
IMAGE=$(find_latest_image "${GPU_ARCH}")
# Try the local docker registry first (avoids Docker Hub rate limits and is
# faster on the LAN); if that fails for any reason, fall back to the
# public registry with exponential-backoff retries. Capture stderr so the
# real failure reason (TLS handshake, 404, connection refused, etc.) is
# visible in the job log instead of being silently swallowed.
if local_pull_output=$(docker pull "${LOCAL_DOCKER_REGISTRY}/${IMAGE}" 2>&1); then
echo "Pulled from local docker registry: ${LOCAL_DOCKER_REGISTRY}/${IMAGE}"
docker tag "${LOCAL_DOCKER_REGISTRY}/${IMAGE}" "${IMAGE}"
# Determine which image to use
if [[ -n "${CUSTOM_IMAGE}" ]]; then
IMAGE="${CUSTOM_IMAGE}"
echo "Using custom image: ${IMAGE}"
if [[ "${IMAGE}" == "${LOCAL_DOCKER_REGISTRY}/"* ]]; then
docker pull "${IMAGE}"
else
retry_with_backoff 6 docker pull "${IMAGE}"
fi
else
echo "Local docker registry pull failed; falling back to public registry: ${IMAGE}" >&2
printf '%s\n' "${local_pull_output}" | sed 's/^/ [local-pull] /' >&2
retry_with_backoff 6 docker pull "${IMAGE}"
IMAGE=$(find_latest_image "${GPU_ARCH}")
# Try the local docker registry first (avoids Docker Hub rate limits and is
# faster on the LAN); if that fails for any reason, fall back to the
# public registry with exponential-backoff retries. Capture stderr so the
# real failure reason (TLS handshake, 404, connection refused, etc.) is
# visible in the job log instead of being silently swallowed.
if local_pull_output=$(docker pull "${LOCAL_DOCKER_REGISTRY}/${IMAGE}" 2>&1); then
echo "Pulled from local docker registry: ${LOCAL_DOCKER_REGISTRY}/${IMAGE}"
docker tag "${LOCAL_DOCKER_REGISTRY}/${IMAGE}" "${IMAGE}"
else
echo "Local docker registry pull failed; falling back to public registry: ${IMAGE}" >&2
printf '%s\n' "${local_pull_output}" | sed 's/^/ [local-pull] /' >&2
retry_with_backoff 6 docker pull "${IMAGE}"
fi
fi
CACHE_HOST=/home/runner/sglang-data