laya-ad / code /.github /workflows /docker-release.yml

laya-ad v1.1：六精度权重 + 模型卡 + 项目代码快照

71dabc7 verified 9 days ago

7 kB

name: Build and push laya-server images

# 三类产物：
# 1. 单精度镜像 <版本>-<精度>（fp32/fp16/bf16/fp8/int8/int4）——构建时自动从 Release
#    最新稳定名资产 laya-ad-fp32.tar.gz 拉权重，镜像内量化并烘焙模型 id（laya-<版本>-<精度>）
# 2. 多精度镜像 <版本>-multi——镜像不带权重，管理员经 /internal/models/catalog 自选精度下载
# 3. 稳定名量化资产回传 Release（laya-ad-<精度>.tar.gz，去除名称里的版本号），并清理旧带版本号资产
# latest 与裸版本 tag = fp8。

on:
  release:
    types: [published]
  workflow_dispatch:
    inputs:
      tag:
        description: "镜像版本号（如 v1.0；留空取最新 Release 的 tag）"
        required: false

permissions:
  contents: read
  packages: write

concurrency:
  group: laya-server-docker
  cancel-in-progress: false

jobs:
  backend-tests:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4
      - uses: actions/setup-python@v5
        with:
          python-version: "3.12"
      - name: Install deps
        run: |
          pip install torch --index-url https://download.pytorch.org/whl/cpu
          pip install transformers==5.20.2 "safetensors>=0.6.0" \
            'fastapi==0.141.1' 'uvicorn==0.53.0' 'argon2-cffi==25.1.0' \
            'pydantic==2.13.5' 'httpx==0.28.1' 'pytest==9.1.1'
      - name: Backend tests (ad-clf)
        run: cd laya-server/backend && python -m pytest tests/test_ad_classifier.py -q

  resolve-tag:
    runs-on: ubuntu-latest
    outputs:
      tag: ${{ steps.tag.outputs.tag }}
    steps:
      - id: tag
        env:
          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
        run: |
          if [ -n "${{ inputs.tag }}" ]; then
            TAG="${{ inputs.tag }}"
          elif [ -n "${{ github.event.release.tag_name }}" ]; then
            TAG="${{ github.event.release.tag_name }}"
          else
            TAG="$(gh release view --repo ${{ github.repository }} --json tagName --jq .tagName)"
          fi
          echo "tag=$TAG" >> "$GITHUB_OUTPUT"
  build-single:
    needs: [backend-tests, resolve-tag]
    runs-on: ubuntu-latest
    strategy:
      fail-fast: false
      matrix:
        precision: [fp32, fp16, bf16, fp8, int8, int4]
    steps:
      - uses: actions/checkout@v4
      - uses: docker/setup-buildx-action@v3
      - uses: docker/login-action@v3
        with:
          registry: ghcr.io
          username: ${{ github.actor }}
          password: ${{ secrets.GITHUB_TOKEN }}
      - name: Build and push ${{ needs.resolve-tag.outputs.tag }}-${{ matrix.precision }}
        uses: docker/build-push-action@v6
        with:
          context: laya-server
          target: single
          push: true
          platforms: linux/amd64
          build-args: |
            PRECISION=${{ matrix.precision }}
            MODEL_ID=laya-${{ needs.resolve-tag.outputs.tag }}-${{ matrix.precision }}
          tags: ghcr.io/${{ github.repository_owner }}/laya-server:${{ needs.resolve-tag.outputs.tag }}-${{ matrix.precision }}
          cache-from: type=gha,scope=laya-${{ matrix.precision }}
          cache-to: type=gha,mode=max,scope=laya-${{ matrix.precision }}

  build-multi:
    needs: [backend-tests, resolve-tag]
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4
      - uses: docker/setup-buildx-action@v3
      - uses: docker/login-action@v3
        with:
          registry: ghcr.io
          username: ${{ github.actor }}
          password: ${{ secrets.GITHUB_TOKEN }}
      - name: Build and push ${{ needs.resolve-tag.outputs.tag }}-multi
        uses: docker/build-push-action@v6
        with:
          context: laya-server
          target: multi
          push: true
          platforms: linux/amd64
          tags: ghcr.io/${{ github.repository_owner }}/laya-server:${{ needs.resolve-tag.outputs.tag }}-multi
          cache-from: type=gha,scope=laya-multi
          cache-to: type=gha,mode=max,scope=laya-multi

  version-tags:
    needs: [build-single, resolve-tag]
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4
      - uses: docker/setup-buildx-action@v3
      - uses: docker/login-action@v3
        with:
          registry: ghcr.io
          username: ${{ github.actor }}
          password: ${{ secrets.GITHUB_TOKEN }}
      - name: Push latest and bare version tags (fp8)
        uses: docker/build-push-action@v6
        with:
          context: laya-server
          target: single
          push: true
          platforms: linux/amd64
          build-args: |
            PRECISION=fp8
            MODEL_ID=laya-${{ needs.resolve-tag.outputs.tag }}
          tags: |
            ghcr.io/${{ github.repository_owner }}/laya-server:latest
            ghcr.io/${{ github.repository_owner }}/laya-server:${{ needs.resolve-tag.outputs.tag }}
          cache-from: type=gha,scope=laya-fp8
          cache-to: type=gha,scope=laya-fp8,mode=max

  stable-assets:
    needs: [backend-tests, resolve-tag]
    runs-on: ubuntu-latest
    permissions:
      contents: write
    env:
      GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
      TAG: ${{ needs.resolve-tag.outputs.tag }}
    steps:
      - uses: actions/checkout@v4
      - uses: actions/setup-python@v5
        with:
          python-version: "3.12"
      - name: Install quantization deps
        run: |
          pip install torch --index-url https://download.pytorch.org/whl/cpu
          pip install transformers==5.20.2 "safetensors>=0.6.0"
      - name: Download fp32 base
        run: |
          gh release download "$TAG" --repo ${{ github.repository }} \
            -p 'laya-ad-fp32.tar.gz' -O fp32.tar.gz
          tar xzf fp32.tar.gz
          # 包内层目录名随打包方式变化（laya-ad-vX.Y-fp32 / fp32），按 config.json 定位
          SRC=$(find . -maxdepth 2 -type f -name config.json -not -path './.git/*' -not -path '*/node_modules/*' | head -1)
          test -n "$SRC" || { echo '未找到解压后的模型目录' >&2; exit 1; }
          SRC=$(dirname "$SRC")
          test -s "$SRC/model.safetensors" || { echo "缺少 model.safetensors: $SRC" >&2; exit 1; }
          echo "SRC=$SRC" >> "$GITHUB_ENV"
      - name: Quantize all precisions
        run: |
          python scripts/quantize_variants.py --src "$SRC" --out build/variants \
            --variants fp32,fp16,bf16,fp8,int8,int4
      - name: Upload stable-name assets
        run: |
          for p in fp32 fp16 bf16 fp8 int8 int4; do
            echo "$TAG" > "build/variants/$p/VERSION.txt"
            tar czf "laya-ad-$p.tar.gz" -C build/variants "$p"
            gh release upload "$TAG" "laya-ad-$p.tar.gz" --repo ${{ github.repository }} --clobber
          done
      - name: Remove versioned assets from release
        run: |
          for p in fp32 fp16 bf16 fp8 int8 int4; do
            gh release delete-asset "$TAG" "laya-ad-$TAG-$p.tar.gz" \
              --repo ${{ github.repository }} --yes || true
          done

	name: Build and push laya-server images

	# 三类产物：
	# 1. 单精度镜像 <版本>-<精度>（fp32/fp16/bf16/fp8/int8/int4）——构建时自动从 Release
	# 最新稳定名资产 laya-ad-fp32.tar.gz 拉权重，镜像内量化并烘焙模型 id（laya-<版本>-<精度>）
	# 2. 多精度镜像 <版本>-multi——镜像不带权重，管理员经 /internal/models/catalog 自选精度下载
	# 3. 稳定名量化资产回传 Release（laya-ad-<精度>.tar.gz，去除名称里的版本号），并清理旧带版本号资产
	# latest 与裸版本 tag = fp8。

	on:
	release:
	types: [published]
	workflow_dispatch:
	inputs:
	tag:
	description: "镜像版本号（如 v1.0；留空取最新 Release 的 tag）"
	required: false

	permissions:
	contents: read
	packages: write

	concurrency:
	group: laya-server-docker
	cancel-in-progress: false

	jobs:
	backend-tests:
	runs-on: ubuntu-latest
	steps:
	- uses: actions/checkout@v4
	- uses: actions/setup-python@v5
	with:
	python-version: "3.12"
	- name: Install deps
	run: \|
	pip install torch --index-url https://download.pytorch.org/whl/cpu
	pip install transformers==5.20.2 "safetensors>=0.6.0" \
	'fastapi==0.141.1' 'uvicorn==0.53.0' 'argon2-cffi==25.1.0' \
	'pydantic==2.13.5' 'httpx==0.28.1' 'pytest==9.1.1'
	- name: Backend tests (ad-clf)
	run: cd laya-server/backend && python -m pytest tests/test_ad_classifier.py -q

	resolve-tag:
	runs-on: ubuntu-latest
	outputs:
	tag: ${{ steps.tag.outputs.tag }}
	steps:
	- id: tag
	env:
	GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
	run: \|
	if [ -n "${{ inputs.tag }}" ]; then
	TAG="${{ inputs.tag }}"
	elif [ -n "${{ github.event.release.tag_name }}" ]; then
	TAG="${{ github.event.release.tag_name }}"
	else
	TAG="$(gh release view --repo ${{ github.repository }} --json tagName --jq .tagName)"
	fi
	echo "tag=$TAG" >> "$GITHUB_OUTPUT"

	build-single:
	needs: [backend-tests, resolve-tag]
	runs-on: ubuntu-latest
	strategy:
	fail-fast: false
	matrix:
	precision: [fp32, fp16, bf16, fp8, int8, int4]
	steps:
	- uses: actions/checkout@v4
	- uses: docker/setup-buildx-action@v3
	- uses: docker/login-action@v3
	with:
	registry: ghcr.io
	username: ${{ github.actor }}
	password: ${{ secrets.GITHUB_TOKEN }}
	- name: Build and push ${{ needs.resolve-tag.outputs.tag }}-${{ matrix.precision }}
	uses: docker/build-push-action@v6
	with:
	context: laya-server
	target: single
	push: true
	platforms: linux/amd64
	build-args: \|
	PRECISION=${{ matrix.precision }}
	MODEL_ID=laya-${{ needs.resolve-tag.outputs.tag }}-${{ matrix.precision }}
	tags: ghcr.io/${{ github.repository_owner }}/laya-server:${{ needs.resolve-tag.outputs.tag }}-${{ matrix.precision }}
	cache-from: type=gha,scope=laya-${{ matrix.precision }}
	cache-to: type=gha,mode=max,scope=laya-${{ matrix.precision }}

	build-multi:
	needs: [backend-tests, resolve-tag]
	runs-on: ubuntu-latest
	steps:
	- uses: actions/checkout@v4
	- uses: docker/setup-buildx-action@v3
	- uses: docker/login-action@v3
	with:
	registry: ghcr.io
	username: ${{ github.actor }}
	password: ${{ secrets.GITHUB_TOKEN }}
	- name: Build and push ${{ needs.resolve-tag.outputs.tag }}-multi
	uses: docker/build-push-action@v6
	with:
	context: laya-server
	target: multi
	push: true
	platforms: linux/amd64
	tags: ghcr.io/${{ github.repository_owner }}/laya-server:${{ needs.resolve-tag.outputs.tag }}-multi
	cache-from: type=gha,scope=laya-multi
	cache-to: type=gha,mode=max,scope=laya-multi

	version-tags:
	needs: [build-single, resolve-tag]
	runs-on: ubuntu-latest
	steps:
	- uses: actions/checkout@v4
	- uses: docker/setup-buildx-action@v3
	- uses: docker/login-action@v3
	with:
	registry: ghcr.io
	username: ${{ github.actor }}
	password: ${{ secrets.GITHUB_TOKEN }}
	- name: Push latest and bare version tags (fp8)
	uses: docker/build-push-action@v6
	with:
	context: laya-server
	target: single
	push: true
	platforms: linux/amd64
	build-args: \|
	PRECISION=fp8
	MODEL_ID=laya-${{ needs.resolve-tag.outputs.tag }}
	tags: \|
	ghcr.io/${{ github.repository_owner }}/laya-server:latest
	ghcr.io/${{ github.repository_owner }}/laya-server:${{ needs.resolve-tag.outputs.tag }}
	cache-from: type=gha,scope=laya-fp8
	cache-to: type=gha,scope=laya-fp8,mode=max

	stable-assets:
	needs: [backend-tests, resolve-tag]
	runs-on: ubuntu-latest
	permissions:
	contents: write
	env:
	GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
	TAG: ${{ needs.resolve-tag.outputs.tag }}
	steps:
	- uses: actions/checkout@v4
	- uses: actions/setup-python@v5
	with:
	python-version: "3.12"
	- name: Install quantization deps
	run: \|
	pip install torch --index-url https://download.pytorch.org/whl/cpu
	pip install transformers==5.20.2 "safetensors>=0.6.0"
	- name: Download fp32 base
	run: \|
	gh release download "$TAG" --repo ${{ github.repository }} \
	-p 'laya-ad-fp32.tar.gz' -O fp32.tar.gz
	tar xzf fp32.tar.gz
	# 包内层目录名随打包方式变化（laya-ad-vX.Y-fp32 / fp32），按 config.json 定位
	SRC=$(find . -maxdepth 2 -type f -name config.json -not -path './.git/' -not -path '/node_modules/*' \| head -1)
	test -n "$SRC" \|\| { echo '未找到解压后的模型目录' >&2; exit 1; }
	SRC=$(dirname "$SRC")
	test -s "$SRC/model.safetensors" \|\| { echo "缺少 model.safetensors: $SRC" >&2; exit 1; }
	echo "SRC=$SRC" >> "$GITHUB_ENV"
	- name: Quantize all precisions
	run: \|
	python scripts/quantize_variants.py --src "$SRC" --out build/variants \
	--variants fp32,fp16,bf16,fp8,int8,int4
	- name: Upload stable-name assets
	run: \|
	for p in fp32 fp16 bf16 fp8 int8 int4; do
	echo "$TAG" > "build/variants/$p/VERSION.txt"
	tar czf "laya-ad-$p.tar.gz" -C build/variants "$p"
	gh release upload "$TAG" "laya-ad-$p.tar.gz" --repo ${{ github.repository }} --clobber
	done
	- name: Remove versioned assets from release
	run: \|
	for p in fp32 fp16 bf16 fp8 int8 int4; do
	gh release delete-asset "$TAG" "laya-ad-$TAG-$p.tar.gz" \
	--repo ${{ github.repository }} --yes \|\| true
	done