minke.yu/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 13 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