94057c3d3e
PR Test (NPU) / check-changes (push) Has been cancelled
PR Test (NPU) / pr-gate (push) Has been cancelled
PR Test (NPU) / set-image-config (push) Has been cancelled
PR Test (NPU) / stage-b-test-1-npu-a2 (0) (push) Has been cancelled
PR Test (NPU) / stage-b-test-1-npu-a2 (1) (push) Has been cancelled
PR Test (NPU) / stage-b-test-2-npu-a2 (0) (push) Has been cancelled
PR Test (NPU) / stage-b-test-2-npu-a2 (1) (push) Has been cancelled
PR Test (NPU) / stage-b-test-4-npu-a3 (push) Has been cancelled
PR Test (NPU) / stage-b-test-16-npu-a3 (push) Has been cancelled
PR Test (NPU) / multimodal-gen-test-1-npu-a3 (push) Has been cancelled
PR Test (NPU) / multimodal-gen-test-2-npu-a3 (push) Has been cancelled
PR Test (Arm64) / pr-gate (push) Has been cancelled
PR Test (Arm64) / check-changes (push) Has been cancelled
PR Test (Arm64) / build-test (push) Has been cancelled
PR Test (sgl-router) / gate (push) Has been cancelled
PR Test (sgl-router) / tier-1 — lint (push) Has been cancelled
PR Test (sgl-router) / tier-2 — build + test (push) Has been cancelled
PR Test (sgl-router) / tier-3 — docker (placeholder) (push) Has been cancelled
PR Test (sgl-router) / tier-3 — k8s integration (push) Has been cancelled
PR Test (sgl-router) / tier-3 — e2e (push) Has been cancelled
PR Test (sgl-router) / finish (push) Has been cancelled
PR Test (NPU) / single-node-poc (map[name:qwen3_6_27b_w8a8_1p_in64k_out1k_50ms runner:linux-aarch64-a3-2 test_case:test/registered/ascend/performance/qwen3_6_27b/test_npu_qwen3_6_27b_w8a8_1p_in64k_out1k_50ms.py test_type:perf]) (push) Has been cancelled
PR Test (NPU) / pr-test-npu-finish (push) Has been cancelled
PR Test (Xeon) / pr-gate (push) Has been cancelled
PR Test (Xeon) / check-changes (push) Has been cancelled
PR Test (Xeon) / build-test (, xeon-gnr, base-b-test-cpu) (push) Has been cancelled
PR Test (XPU) / check-changes (push) Has been cancelled
PR Test (XPU) / pr-gate (push) Has been cancelled
PR Test (XPU) / stage-a-test-1-gpu-xpu (push) Has been cancelled
PR Test (XPU) / wait-for-stage-a (push) Has been cancelled
PR Test (XPU) / stage-b-test-1-gpu-xpu (push) Has been cancelled
PR Test (XPU) / finish (push) Has been cancelled
CI Model Inventory / build-inventory (push) Has been cancelled
Lint / lint (push) Has been cancelled
PR Benchmark (SMG Components) / Benchmark Compilation Check (push) Has been cancelled
PR Benchmark (SMG Components) / Benchmark - Manual Policy (push) Has been cancelled
PR Benchmark (SMG Components) / Benchmark - Request Processing (push) Has been cancelled
PR Benchmark (SMG Components) / Benchmark Summary (push) Has been cancelled
PR Test (SMG) / build-wheel (push) Has been cancelled
Release SGLang Model Gateway to PyPI / build on windows (x86_64 - auto) (push) Has been cancelled
Release SGLang Model Gateway to PyPI / build on macos (x86_64 - auto) (push) Has been cancelled
PR Test (SMG) / python-unit-tests (push) Has been cancelled
PR Test (SMG) / unit-tests (push) Has been cancelled
PR Test (SMG) / benchmarks (push) Has been cancelled
PR Test (SMG) / chat-completions (push) Has been cancelled
PR Test (SMG) / chat-completions-4gpu (push) Has been cancelled
PR Test (SMG) / e2e (push) Has been cancelled
PR Test (SMG) / docker-build-test (push) Has been cancelled
PR Test (SMG) / k8s-integration (push) Has been cancelled
PR Test (SMG) / finish (push) Has been cancelled
PR Test (SMG) / summarize-benchmarks (push) Has been cancelled
Release SGLang Model Gateway Docker Image / publish (push) Has been cancelled
Release SGLang Model Gateway to PyPI / build on macos (aarch64 - auto) (push) Has been cancelled
Release SGLang Model Gateway to PyPI / build on linux (aarch64 - auto) (push) Has been cancelled
Release SGLang Model Gateway to PyPI / build on linux (x86_64 - auto) (push) Has been cancelled
Release SGLang Model Gateway to PyPI / build on linux (aarch64 - musllinux_1_1) (push) Has been cancelled
Release SGLang Model Gateway to PyPI / build on linux (x86_64 - musllinux_1_1) (push) Has been cancelled
Release SGLang Model Gateway to PyPI / Build SDist (push) Has been cancelled
Release SGLang Model Gateway to PyPI / Upload to PyPI (push) Has been cancelled
Release SGLang Kernels / build-cu129-matrix (aarch64, 12.9, 3.10, arm-kernel-build-node) (push) Has been cancelled
Release SGLang Kernels / build-cu129-matrix (x86_64, 12.9, 3.10, x64-kernel-build-node) (push) Has been cancelled
Release SGLang Kernels / release-cu129 (push) Has been cancelled
Release SGLang Kernels / build-cu130-matrix (aarch64, 13.0, 3.10, arm-kernel-build-node) (push) Has been cancelled
Release SGLang Kernels / build-cu130-matrix (x86_64, 13.0, 3.10, x64-kernel-build-node) (push) Has been cancelled
Release SGLang Kernels / release-cu130 (push) Has been cancelled
Release SGLang Kernels / build-rocm-matrix (3.10, 700) (push) Has been cancelled
Release SGLang Kernels / build-rocm-matrix (3.10, 720) (push) Has been cancelled
Release SGLang Kernels / release-rocm700 (push) Has been cancelled
Release SGLang Kernels / release-rocm720 (push) Has been cancelled
Release SGLang Kernels / build-musa43 (43, 3.10) (push) Has been cancelled
Release SGLang Kernels / release-musa43 (push) Has been cancelled
94 lines
3.1 KiB
YAML
94 lines
3.1 KiB
YAML
name: Release Docker Images (NPU)
|
|
on:
|
|
push:
|
|
tags:
|
|
- 'v[0-9]+.*'
|
|
workflow_dispatch:
|
|
inputs:
|
|
version:
|
|
description: 'Version to build (without v prefix, e.g., 0.5.7)'
|
|
required: true
|
|
|
|
jobs:
|
|
build:
|
|
runs-on: ubuntu-22.04-arm
|
|
strategy:
|
|
matrix:
|
|
cann_version: ["9.0.0"]
|
|
device_type: ["910b", "a3"]
|
|
steps:
|
|
- name: Checkout repository
|
|
uses: actions/checkout@v4
|
|
|
|
- name: Free up disk space
|
|
uses: jlumbroso/free-disk-space@54081f138730dfa15788a46383842cd2f914a1be # v1.3.1
|
|
with:
|
|
tool-cache: true
|
|
docker-images: false
|
|
|
|
# push with tag
|
|
- name: Docker meta
|
|
id: meta
|
|
uses: docker/metadata-action@v5
|
|
with:
|
|
images: |
|
|
lmsysorg/sglang
|
|
tags: |
|
|
type=ref,event=pr
|
|
flavor: |
|
|
latest=false
|
|
|
|
# Login against a Docker registry except on PR
|
|
# https://github.com/docker/login-action
|
|
- name: Login to Docker Hub
|
|
uses: docker/login-action@v2
|
|
if: ${{ github.repository == 'sgl-project/sglang' && github.event_name != 'pull_request' }}
|
|
with:
|
|
username: ${{ secrets.DOCKERHUB_USERNAME }}
|
|
password: ${{ secrets.DOCKERHUB_TOKEN }}
|
|
|
|
- name: Get version from tag
|
|
id: version
|
|
run: |
|
|
if [ "${{ github.event_name }}" = "workflow_dispatch" ]; then
|
|
VERSION="${{ github.event.inputs.version }}"
|
|
else
|
|
# Extract version from tag (e.g., v0.5.7 -> 0.5.7)
|
|
VERSION="${GITHUB_REF_NAME#v}"
|
|
fi
|
|
# Validate version format
|
|
if [ -z "$VERSION" ]; then
|
|
echo "::error::Version is empty"
|
|
exit 1
|
|
fi
|
|
if ! echo "$VERSION" | grep -qE '^[0-9]+\.[0-9]+\.[0-9]+'; then
|
|
echo "::error::Invalid version format: $VERSION (expected: X.Y.Z)"
|
|
exit 1
|
|
fi
|
|
echo "version=v${VERSION}" >> $GITHUB_OUTPUT
|
|
echo "TAG=lmsysorg/sglang:v${VERSION}-cann${{ matrix.cann_version }}-${{ matrix.device_type }}" >> $GITHUB_OUTPUT
|
|
# Enable Docker multi-architecture build environment
|
|
# Emulate non-native architectures
|
|
- name: Set up QEMU
|
|
uses: docker/setup-qemu-action@v3
|
|
# Required for building and pushing multi-arch Docker images
|
|
- name: Set up Docker Buildx
|
|
uses: docker/setup-buildx-action@v3
|
|
|
|
- name: Build and push Docker image
|
|
id: build-and-push
|
|
uses: docker/build-push-action@v6
|
|
with:
|
|
context: docker
|
|
file: docker/npu.Dockerfile
|
|
platforms: linux/arm64,linux/amd64
|
|
labels: ${{ steps.meta.outputs.labels }}
|
|
tags: ${{ steps.meta.outputs.tags || steps.version.outputs.TAG }}
|
|
push: ${{ github.repository == 'sgl-project/sglang' && github.event_name != 'pull_request' }}
|
|
provenance: false
|
|
build-args: |
|
|
SGLANG_KERNEL_NPU_TAG=2026.6.2
|
|
CANN_VERSION=${{ matrix.cann_version }}
|
|
DEVICE_TYPE=${{ matrix.device_type }}
|
|
SGLANG_TAG=${{ steps.version.outputs.version }}
|