flan/winnow
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: add ROCm (AMD GPU) and Intel GPU support (v0.2.12)

Browse Source 
New image variants:
- :rocm  — InsightFace via ROCmExecutionProvider, SigLIP via PyTorch ROCm 6.3
- :intel — InsightFace via OpenVINOExecutionProvider (onnxruntime-openvino);
           Intel GPU compute runtime auto-installed from Intel graphics repo;
           OPENVINO_DEVICE=GPU opts into Arc/iGPU inference (default: CPU)

Also adds:
- pyproject-rocm.toml + uv-rocm.lock, pyproject-intel.toml + uv-intel.lock
- compose.yml device passthrough snippets for AMD and Intel
- CI: build-rocm and build-intel jobs in docker-publish.yml; all four
  variants built and tagged in release.yml
- README reworked: cleaner structure, GPU variant quick-start examples,
  OPENVINO_DEVICE env var documented
- CHANGELOG entry and version bump to 0.2.12

Fix: IntPrompt in dict literal was eagerly evaluated in the no-embedding
fallback path of _get_strategy_choice, prompting users for a custom count
regardless of which strategy they picked.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
flan
2026-06-13 02:31:09 +00:00
co-authored by Claude Sonnet 4.6
parent a281b4b896
commit b2be19e259
16 changed files with 4550 additions and 183 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.github/workflows/docker-publish.yml
+124
View File
@@ -199,3 +199,127 @@ jobs:
-f visibility=public || true
env:
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
build-rocm:
name: Build ROCm / AMD GPU (amd64)
runs-on: ubuntu-latest
permissions:
contents: read
packages: write
steps:
- name: Free up disk space
run: |
sudo rm -rf /usr/share/dotnet
sudo rm -rf /opt/ghc
sudo rm -rf "/usr/local/share/boost"
sudo rm -rf "$AGENT_TOOLSDIRECTORY"
echo "Disk space freed."
- name: Checkout repository
uses: actions/checkout@v6
- name: Set up Docker Buildx
uses: docker/setup-buildx-action@v4
- name: Log in to GHCR
uses: docker/login-action@v4
with:
registry: ${{ env.REGISTRY }}
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
- name: Determine ROCm image tag
id: rocm-tag
run: |
if [ "${{ github.ref_name }}" = "dev" ]; then
echo "tag=${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}:dev-rocm" >> "$GITHUB_OUTPUT"
else
echo "tag=${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}:rocm" >> "$GITHUB_OUTPUT"
fi
- name: Build and push ROCm image
uses: docker/build-push-action@v6
with:
context: .
file: ./Dockerfile
platforms: linux/amd64
build-args: VARIANT=rocm
cache-from: type=gha,scope=linux/amd64-rocm
cache-to: type=gha,mode=max,scope=linux/amd64-rocm
github-token: ${{ secrets.GITHUB_TOKEN }}
push: true
tags: ${{ steps.rocm-tag.outputs.tag }}
- name: Inspect ROCm image
run: |
docker buildx imagetools inspect ${{ steps.rocm-tag.outputs.tag }}
- name: Ensure package is public
run: |
gh api -X PATCH /user/packages/container/winnow \
-f visibility=public || true
env:
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
build-intel:
name: Build Intel GPU (amd64)
runs-on: ubuntu-latest
permissions:
contents: read
packages: write
steps:
- name: Free up disk space
run: |
sudo rm -rf /usr/share/dotnet
sudo rm -rf /opt/ghc
sudo rm -rf "/usr/local/share/boost"
sudo rm -rf "$AGENT_TOOLSDIRECTORY"
echo "Disk space freed."
- name: Checkout repository
uses: actions/checkout@v6
- name: Set up Docker Buildx
uses: docker/setup-buildx-action@v4
- name: Log in to GHCR
uses: docker/login-action@v4
with:
registry: ${{ env.REGISTRY }}
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
- name: Determine Intel image tag
id: intel-tag
run: |
if [ "${{ github.ref_name }}" = "dev" ]; then
echo "tag=${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}:dev-intel" >> "$GITHUB_OUTPUT"
else
echo "tag=${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}:intel" >> "$GITHUB_OUTPUT"
fi
- name: Build and push Intel image
uses: docker/build-push-action@v6
with:
context: .
file: ./Dockerfile
platforms: linux/amd64
build-args: VARIANT=intel
cache-from: type=gha,scope=linux/amd64-intel
cache-to: type=gha,mode=max,scope=linux/amd64-intel
github-token: ${{ secrets.GITHUB_TOKEN }}
push: true
tags: ${{ steps.intel-tag.outputs.tag }}
- name: Inspect Intel image
run: |
docker buildx imagetools inspect ${{ steps.intel-tag.outputs.tag }}
- name: Ensure package is public
run: |
gh api -X PATCH /user/packages/container/winnow \
-f visibility=public || true
env:
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
.github/workflows/release.yml
+45 -3
View File
@@ -118,15 +118,57 @@ jobs:
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
- name: Build and push Docker image
- name: Build and push GPU image (latest)
uses: docker/build-push-action@v6
with:
context: .
file: ./Dockerfile
platforms: linux/amd64,linux/arm64
push: true
cache-from: type=gha
cache-to: type=gha,mode=max
cache-from: type=gha,scope=release-gpu
cache-to: type=gha,mode=max,scope=release-gpu
tags: |
ghcr.io/sudolulo/winnow:latest
ghcr.io/sudolulo/winnow:${{ steps.tag.outputs.TAG }}
- name: Build and push CPU image
uses: docker/build-push-action@v6
with:
context: .
file: ./Dockerfile
platforms: linux/amd64,linux/arm64
build-args: VARIANT=cpu
push: true
cache-from: type=gha,scope=release-cpu
cache-to: type=gha,mode=max,scope=release-cpu
tags: |
ghcr.io/sudolulo/winnow:cpu
ghcr.io/sudolulo/winnow:${{ steps.tag.outputs.TAG }}-cpu
- name: Build and push ROCm image
uses: docker/build-push-action@v6
with:
context: .
file: ./Dockerfile
platforms: linux/amd64
build-args: VARIANT=rocm
push: true
cache-from: type=gha,scope=release-rocm
cache-to: type=gha,mode=max,scope=release-rocm
tags: |
ghcr.io/sudolulo/winnow:rocm
ghcr.io/sudolulo/winnow:${{ steps.tag.outputs.TAG }}-rocm
- name: Build and push Intel image
uses: docker/build-push-action@v6
with:
context: .
file: ./Dockerfile
platforms: linux/amd64
build-args: VARIANT=intel
push: true
cache-from: type=gha,scope=release-intel
cache-to: type=gha,mode=max,scope=release-intel
tags: |
ghcr.io/sudolulo/winnow:intel
ghcr.io/sudolulo/winnow:${{ steps.tag.outputs.TAG }}-intel