ci: refactor big model chunk handling (#1939)

This commit is contained in:
Jason Wen
2026-08-23 02:48:10 -04:00
committed by GitHub
parent 086530b7c6
commit 34621cf816
@@ -211,6 +211,8 @@ jobs:
needs: [ prepare_strategy ]
runs-on: ubuntu-24.04
if: ${{ needs.prepare_strategy.outputs.include_big_model == 'true' }}
outputs:
onnx_sha256: ${{ steps.resolve.outputs.onnx_sha256 }}
env:
HF_REPO: sunnypilot/sunnypilot_models_v1
HF_DEFAULTS_PATH: models/defaults/big
@@ -226,6 +228,7 @@ jobs:
run: |
ACTUAL_ONNX_HASH=$(sha256sum "openpilot/selfdrive/modeld/models/big_driving_supercombo.onnx" | cut -d' ' -f1)
echo "Repo ONNX hash: $ACTUAL_ONNX_HASH"
echo "onnx_sha256=$ACTUAL_ONNX_HASH" >> $GITHUB_OUTPUT
JSON_URL="https://huggingface.co/datasets/${HF_REPO}/resolve/main/${HF_DEFAULTS_PATH}/default_models.json"
@@ -267,36 +270,6 @@ jobs:
env:
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
- name: Download big model chunks
run: |
ACTUAL_ONNX_HASH=$(sha256sum "openpilot/selfdrive/modeld/models/big_driving_supercombo.onnx" | cut -d' ' -f1)
JSON_URL="https://huggingface.co/datasets/${HF_REPO}/resolve/main/${HF_DEFAULTS_PATH}/default_models.json"
DEFAULTS=$(curl -fsSL "$JSON_URL")
BUNDLE=$(echo "$DEFAULTS" | jq --arg hash "$ACTUAL_ONNX_HASH" '.bundles[] | select(.onnx_sha256 == $hash)')
mkdir -p big_model_chunks
ARTIFACT=$(echo "$BUNDLE" | jq -r '.models[0].artifact')
BASE_URL=$(echo "$ARTIFACT" | jq -r '.download_uri.url' | sed 's|/[^/]*$||')
NUM_CHUNKS=$(echo "$ARTIFACT" | jq -r '.chunks | length')
CANONICAL="big_driving_tinygrad.pkl"
echo "$ARTIFACT" | jq -r '.chunks[].file_name' | while read CHUNK_NAME; do
CHUNK_IDX=$(echo "$CHUNK_NAME" | grep -oP 'chunk\K[0-9]+of[0-9]+')
CANONICAL_CHUNK="${CANONICAL}.chunk${CHUNK_IDX}"
ENCODED_URL=$(python3 -c "import urllib.parse; print(urllib.parse.quote('${BASE_URL}/${CHUNK_NAME}', safe=':/'))")
echo "Downloading $CHUNK_NAME -> $CANONICAL_CHUNK"
curl -fsSL -o "big_model_chunks/${CANONICAL_CHUNK}" "$ENCODED_URL"
done
echo "$NUM_CHUNKS" > "big_model_chunks/${CANONICAL}.chunkmanifest"
- name: Upload big model chunks
uses: actions/upload-artifact@v4
with:
name: big-model-chunks
path: big_model_chunks/
compression-level: 0
- name: Cancel run on failure
if: failure()
run: gh run cancel ${{ github.run_id }}
@@ -339,12 +312,32 @@ jobs:
mkdir -p "${{ github.workspace }}/chestnut_output"
tar xzf prebuilt.tar.gz -C "${{ github.workspace }}/chestnut_output"
- name: Download big model chunks
- name: Download big model chunks from HF
if: ${{ needs.prepare_chestnut.result == 'success' }}
uses: actions/download-artifact@v4
with:
name: big-model-chunks
path: big_model_chunks
env:
HF_REPO: sunnypilot/sunnypilot_models_v1
HF_DEFAULTS_PATH: models/defaults/big
run: |
ONNX_HASH="${{ needs.prepare_chestnut.outputs.onnx_sha256 }}"
JSON_URL="https://huggingface.co/datasets/${HF_REPO}/resolve/main/${HF_DEFAULTS_PATH}/default_models.json"
DEFAULTS=$(curl -fsSL "$JSON_URL")
BUNDLE=$(echo "$DEFAULTS" | jq --arg hash "$ONNX_HASH" '.bundles[] | select(.onnx_sha256 == $hash)')
mkdir -p big_model_chunks
ARTIFACT=$(echo "$BUNDLE" | jq -r '.models[0].artifact')
BASE_URL=$(echo "$ARTIFACT" | jq -r '.download_uri.url' | sed 's|/[^/]*$||')
NUM_CHUNKS=$(echo "$ARTIFACT" | jq -r '.chunks | length')
CANONICAL="big_driving_tinygrad.pkl"
echo "$ARTIFACT" | jq -r '.chunks[].file_name' | while read CHUNK_NAME; do
CHUNK_IDX=$(echo "$CHUNK_NAME" | grep -oP 'chunk\K[0-9]+of[0-9]+')
CANONICAL_CHUNK="${CANONICAL}.chunk${CHUNK_IDX}"
ENCODED_URL=$(python3 -c "import urllib.parse; print(urllib.parse.quote('${BASE_URL}/${CHUNK_NAME}', safe=':/'))")
echo "Downloading $CHUNK_NAME -> $CANONICAL_CHUNK"
curl -fsSL -o "big_model_chunks/${CANONICAL_CHUNK}" "$ENCODED_URL"
done
echo "$NUM_CHUNKS" > "big_model_chunks/${CANONICAL}.chunkmanifest"
- name: Inject big model into chestnut
if: ${{ needs.prepare_chestnut.result == 'success' }}