Files
sunnypilot/.github/workflows/build-default-models.yaml
T
Jason Wen 6cc5f3aad8 ci: fix DM model build, separate HF defaults paths, nuke build races (#1956)
* ci: fix DM model build, separate HF defaults paths, nuke build races

* more split!

* name

* ci: download driving and DM model chunks into chestnut prebuilt output
2026-08-24 20:02:48 -04:00

502 lines
20 KiB
YAML

name: Build default models
on:
workflow_dispatch:
inputs:
target:
description: 'Model target to build'
required: true
type: choice
options:
- small
- big
- dm
workflow_call:
inputs:
target:
description: 'Model target to build (small, big, or dm)'
required: true
type: string
concurrency:
group: build-default-models-${{ inputs.target }}
cancel-in-progress: false
env:
HF_REPO: sunnypilot/sunnypilot_models_v1
jobs:
resolve:
runs-on: ubuntu-24.04
outputs:
model_name: ${{ steps.resolve.outputs.model_name }}
onnx_ref: ${{ steps.resolve.outputs.onnx_ref }}
onnx_path: ${{ steps.resolve.outputs.onnx_path }}
hf_defaults_path: ${{ steps.resolve.outputs.hf_defaults_path }}
tinygrad_ref: ${{ steps.resolve.outputs.tinygrad_ref }}
steps:
- uses: actions/checkout@v4
with:
submodules: recursive
- id: resolve
run: |
export PYTHONPATH=${{ github.workspace }}
if [ "${{ inputs.target }}" = "big" ]; then
NAME=$(python3 -c "from openpilot.sunnypilot.models.model_name import DEFAULT_BIG_MODEL; print(DEFAULT_BIG_MODEL)")
ONNX_PATH="openpilot/selfdrive/modeld/models/big_driving_supercombo.onnx"
HF_DEFAULTS_PATH="models/defaults/big"
elif [ "${{ inputs.target }}" = "dm" ]; then
ONNX_PATH="openpilot/selfdrive/modeld/models/dmonitoring_model.onnx"
HF_DEFAULTS_PATH="models/defaults/dm"
NAME="dmonitoring_model ($(git log -1 --format=%cd --date=format:'%B %d, %Y' -- "$ONNX_PATH"))"
else
NAME=$(python3 -c "from openpilot.sunnypilot.models.model_name import DEFAULT_MODEL; print(DEFAULT_MODEL)")
ONNX_PATH="openpilot/selfdrive/modeld/models/driving_supercombo.onnx"
HF_DEFAULTS_PATH="models/defaults/small"
fi
ONNX_REF=$(git log -1 --format='%H' -- "$ONNX_PATH")
TINYGRAD_REF=$(python3 openpilot/sunnypilot/models/tinygrad_ref.py)
if [ -z "$TINYGRAD_REF" ]; then
echo "::error::Failed to resolve tinygrad ref"
exit 1
fi
echo "model_name=${NAME}" >> $GITHUB_OUTPUT
echo "onnx_ref=${ONNX_REF}" >> $GITHUB_OUTPUT
echo "onnx_path=${ONNX_PATH}" >> $GITHUB_OUTPUT
echo "hf_defaults_path=${HF_DEFAULTS_PATH}" >> $GITHUB_OUTPUT
echo "tinygrad_ref=${TINYGRAD_REF}" >> $GITHUB_OUTPUT
build_small_model:
needs: resolve
if: ${{ inputs.target == 'small' }}
runs-on: [self-hosted, tici]
env:
SMALL_ONNX: openpilot/selfdrive/modeld/models/driving_supercombo.onnx
SMALL_PKL: openpilot/selfdrive/modeld/models/driving_tinygrad.pkl
steps:
- uses: actions/checkout@v4
with:
submodules: recursive
- name: Pull ONNX via LFS
run: git lfs pull -I "${{ env.SMALL_ONNX }}"
- name: Set environment variables
run: |
source /etc/profile
export UV_PROJECT_ENVIRONMENT=${HOME}/venv
export UV_PYTHON_PREFERENCE=managed
export UV_PYTHON_INSTALL_DIR=${HOME}/uv/python
export VIRTUAL_ENV=$UV_PROJECT_ENVIRONMENT
uv sync --frozen
printenv >> $GITHUB_ENV
- name: Disable powersave
run: |
source ${UV_PROJECT_ENVIRONMENT}/bin/activate
PYTHONPATH=$PYTHONPATH:${{ github.workspace }}/ ${{ github.workspace }}/scripts/manage-powersave.py --disable
- name: Compile small model with stock compiler
run: |
source ${UV_PROJECT_ENVIRONMENT}/bin/activate
export PYTHONPATH="${PYTHONPATH}:${{ github.workspace }}/tinygrad_repo:${{ github.workspace }}"
MODEL_SIZE=$(python3 -c "from openpilot.common.transformations.model import MEDMODEL_INPUT_SIZE as s; print(f'{s[0]}x{s[1]}')")
CAMERA_RES=$(python3 -c "from openpilot.common.transformations.camera import _ar_ox_fisheye as a, _os_fisheye as o; print(f'{a.width}x{a.height} {o.width}x{o.height}')")
FRAME_SKIP=$(python3 -c "from openpilot.selfdrive.modeld.constants import ModelConstants as MC; print(MC.MODEL_RUN_FREQ // MC.MODEL_CONTEXT_FREQ)")
TG_FLAGS="DEV=QCOM IMAGE=1 FLOAT16=1 NOLOCALS=1 JIT_BATCH_SIZE=0 OPENPILOT_HACKS=1"
env ${TG_FLAGS} python3 \
${{ github.workspace }}/openpilot/selfdrive/modeld/compile_modeld.py \
--onnx ${{ github.workspace }}/${{ env.SMALL_ONNX }} \
--model-size $MODEL_SIZE \
--camera-resolutions $CAMERA_RES \
--frame-skip $FRAME_SKIP \
--output ${{ github.workspace }}/${{ env.SMALL_PKL }}
- name: Chunk small pkl
run: |
source ${UV_PROJECT_ENVIRONMENT}/bin/activate
export PYTHONPATH=${{ github.workspace }}
python3 -c "
from openpilot.common.file_chunker import chunk_file, get_chunk_targets
import os
pkl = '${{ github.workspace }}/${{ env.SMALL_PKL }}'
size = os.path.getsize(pkl)
targets = get_chunk_targets(pkl, size)
chunk_file(pkl, targets)
print(f'Chunked into {len(targets)} files')
"
- name: Prepare output
env:
MODEL_NAME: ${{ needs.resolve.outputs.model_name }}
run: |
source ${UV_PROJECT_ENVIRONMENT}/bin/activate
export PYTHONPATH=${{ github.workspace }}
MODELS_DIR="${{ github.workspace }}/openpilot/selfdrive/modeld/models"
OUTPUT_DIR="${{ github.workspace }}/small_output"
PKL_BASE="driving_tinygrad.pkl"
mkdir -p "$OUTPUT_DIR"
cp "$MODELS_DIR/${PKL_BASE}".chunk* "$OUTPUT_DIR/"
cp "$MODELS_DIR/${PKL_BASE}.chunkmanifest" "$OUTPUT_DIR/"
python3 "${{ github.workspace }}/release/ci/model_generator.py" \
--model-dir "$MODELS_DIR" \
--output-dir "$OUTPUT_DIR" \
--custom-name "$MODEL_NAME" \
--upstream-branch "${{ needs.resolve.outputs.onnx_ref }}"
echo "model-${MODEL_NAME}-${{ github.run_number }}" > "$OUTPUT_DIR/artifact_name.txt"
- name: Upload small model artifact
uses: actions/upload-artifact@v4
with:
name: model-${{ needs.resolve.outputs.model_name }}-${{ github.run_number }}
path: ${{ github.workspace }}/small_output/
- name: Upload artifact name file
uses: actions/upload-artifact@v4
with:
name: artifact-name-${{ needs.resolve.outputs.model_name }}
path: ${{ github.workspace }}/small_output/artifact_name.txt
- name: Re-enable powersave
if: always()
run: |
source ${UV_PROJECT_ENVIRONMENT}/bin/activate
PYTHONPATH=$PYTHONPATH:${{ github.workspace }}/ ${{ github.workspace }}/scripts/manage-powersave.py --enable
build_big_model:
needs: resolve
if: ${{ inputs.target == 'big' }}
runs-on: [self-hosted, usbgpu]
env:
BIG_ONNX: openpilot/selfdrive/modeld/models/big_driving_supercombo.onnx
BIG_PKL: openpilot/selfdrive/modeld/models/big_driving_tinygrad.pkl
steps:
- uses: actions/checkout@v4
with:
submodules: recursive
- name: Pull big ONNX via LFS
run: git lfs pull -I "${{ env.BIG_ONNX }}"
- name: Set environment variables
run: |
source /etc/profile
export UV_PROJECT_ENVIRONMENT=${HOME}/venv
export UV_PYTHON_PREFERENCE=managed
export UV_PYTHON_INSTALL_DIR=${HOME}/uv/python
export VIRTUAL_ENV=$UV_PROJECT_ENVIRONMENT
uv sync --frozen
printenv >> $GITHUB_ENV
- name: Disable powersave
run: |
source ${UV_PROJECT_ENVIRONMENT}/bin/activate
PYTHONPATH=$PYTHONPATH:${{ github.workspace }}/ ${{ github.workspace }}/scripts/manage-powersave.py --disable
- name: Wait for chestnut PCIe link
run: |
source ${UV_PROJECT_ENVIRONMENT}/bin/activate
export PYTHONPATH="${PYTHONPATH}:${{ github.workspace }}/tinygrad_repo:${{ github.workspace }}"
python3 -c "
import time
from openpilot.system.hardware.chestnut.flash import link_up
for i in range(10):
if link_up():
print(f'PCIe link up after {i+1} attempt(s)')
break
time.sleep(1)
else:
raise RuntimeError('Chestnut PCIe link not ready after 10 attempts')
"
- name: Compile big model with stock compiler
run: |
source ${UV_PROJECT_ENVIRONMENT}/bin/activate
export PYTHONPATH="${PYTHONPATH}:${{ github.workspace }}/tinygrad_repo:${{ github.workspace }}"
MODEL_SIZE=$(python3 -c "from openpilot.common.transformations.model import MEDMODEL_INPUT_SIZE as s; print(f'{s[0]}x{s[1]}')")
CAMERA_RES=$(python3 -c "from openpilot.common.transformations.camera import _ar_ox_fisheye as a, _os_fisheye as o; print(f'{a.width}x{a.height} {o.width}x{o.height}')")
FRAME_SKIP=$(python3 -c "from openpilot.selfdrive.modeld.constants import ModelConstants as MC; print(MC.MODEL_RUN_FREQ // MC.MODEL_CONTEXT_FREQ)")
TG_FLAGS="DEBUG=2 DEV=USB+AMD:LLVM WARP_DEV=QCOM FLOAT16=1 JIT_BATCH_SIZE=0 GMMU=0 TC_OPT=2"
env ${TG_FLAGS} python3 \
${{ github.workspace }}/openpilot/selfdrive/modeld/compile_modeld.py \
--onnx ${{ github.workspace }}/${{ env.BIG_ONNX }} \
--model-size $MODEL_SIZE \
--camera-resolutions $CAMERA_RES \
--frame-skip $FRAME_SKIP \
--output ${{ github.workspace }}/${{ env.BIG_PKL }}
- name: Chunk big pkl
run: |
source ${UV_PROJECT_ENVIRONMENT}/bin/activate
export PYTHONPATH=${{ github.workspace }}
python3 -c "
from openpilot.common.file_chunker import chunk_file, get_chunk_targets
import os
pkl = '${{ github.workspace }}/${{ env.BIG_PKL }}'
size = os.path.getsize(pkl)
targets = get_chunk_targets(pkl, size)
chunk_file(pkl, targets)
print(f'Chunked into {len(targets)} files')
"
- name: Prepare output
env:
MODEL_NAME: ${{ needs.resolve.outputs.model_name }}
run: |
source ${UV_PROJECT_ENVIRONMENT}/bin/activate
export PYTHONPATH=${{ github.workspace }}
MODELS_DIR="${{ github.workspace }}/openpilot/selfdrive/modeld/models"
OUTPUT_DIR="${{ github.workspace }}/big_output"
PKL_BASE="big_driving_tinygrad.pkl"
mkdir -p "$OUTPUT_DIR"
cp "$MODELS_DIR/${PKL_BASE}".chunk* "$OUTPUT_DIR/"
cp "$MODELS_DIR/${PKL_BASE}.chunkmanifest" "$OUTPUT_DIR/"
python3 "${{ github.workspace }}/release/ci/model_generator.py" \
--model-dir "$MODELS_DIR" \
--output-dir "$OUTPUT_DIR" \
--custom-name "$MODEL_NAME" \
--upstream-branch "${{ needs.resolve.outputs.onnx_ref }}"
echo "model-${MODEL_NAME}-${{ github.run_number }}" > "$OUTPUT_DIR/artifact_name.txt"
- name: Upload big model artifact
uses: actions/upload-artifact@v4
with:
name: model-${{ needs.resolve.outputs.model_name }}-${{ github.run_number }}
path: ${{ github.workspace }}/big_output/
- name: Upload artifact name file
uses: actions/upload-artifact@v4
with:
name: artifact-name-${{ needs.resolve.outputs.model_name }}
path: ${{ github.workspace }}/big_output/artifact_name.txt
- name: Re-enable powersave
if: always()
run: |
source ${UV_PROJECT_ENVIRONMENT}/bin/activate
PYTHONPATH=$PYTHONPATH:${{ github.workspace }}/ ${{ github.workspace }}/scripts/manage-powersave.py --enable
upload_defaults:
needs: [ resolve, build_small_model, build_big_model, build_dm_model ]
if: |
${{
!cancelled() &&
(inputs.target == 'big' && needs.build_big_model.result == 'success' ||
inputs.target == 'small' && needs.build_small_model.result == 'success' ||
inputs.target == 'dm' && needs.build_dm_model.result == 'success')
}}
runs-on: ubuntu-24.04
permissions:
id-token: write
contents: write
steps:
- uses: actions/checkout@v4
- name: Pull ONNX via LFS
run: git lfs pull -I "${{ needs.resolve.outputs.onnx_path }}"
- name: Install huggingface_hub
run: pip install --upgrade "huggingface_hub>=0.22.0"
- name: Download artifact name
if: ${{ inputs.target == 'small' || inputs.target == 'big' }}
uses: actions/download-artifact@v4
with:
name: artifact-name-${{ needs.resolve.outputs.model_name }}
path: artifact_name
- name: Read artifact name
if: ${{ inputs.target == 'small' || inputs.target == 'big' }}
id: artifact
run: |
ARTIFACT_NAME=$(cat artifact_name/artifact_name.txt)
echo "artifact_name=$ARTIFACT_NAME" >> $GITHUB_OUTPUT
- name: Download model artifact
if: ${{ inputs.target == 'small' || inputs.target == 'big' }}
uses: actions/download-artifact@v4
with:
name: ${{ steps.artifact.outputs.artifact_name }}
path: output
- name: Upload model to HF
if: ${{ inputs.target == 'small' || inputs.target == 'big' }}
env:
HF_OIDC_RESOURCE: datasets/${{ env.HF_REPO }}
ARTIFACT_NAME: ${{ steps.artifact.outputs.artifact_name }}
run: |
rm -f output/artifact_name.txt
export PYTHONPATH=$(pwd)
python3 release/ci/upload_default_model.py \
--hf-repo "${{ env.HF_REPO }}" \
--hf-defaults-path "${{ needs.resolve.outputs.hf_defaults_path }}" \
--artifact-name "$ARTIFACT_NAME" \
--model-dir output \
--onnx-path "${{ needs.resolve.outputs.onnx_path }}" \
--onnx-ref "${{ needs.resolve.outputs.onnx_ref }}" \
--model-name "${{ needs.resolve.outputs.model_name }}" \
--tinygrad-ref "${{ needs.resolve.outputs.tinygrad_ref }}" \
--run-number "${{ github.run_number }}"
- name: Download DM artifact
if: ${{ inputs.target == 'dm' }}
uses: actions/download-artifact@v4
with:
name: dm-model-${{ github.run_number }}
path: dm_output
- name: Generate DM metadata and upload to HF
if: ${{ inputs.target == 'dm' }}
env:
HF_OIDC_RESOURCE: datasets/${{ env.HF_REPO }}
run: |
export PYTHONPATH=$(pwd)
python3 -c "
import json, hashlib
from pathlib import Path
from datetime import datetime, UTC
dm_dir = Path('dm_output')
manifest = list(dm_dir.glob('*.chunkmanifest'))
assert manifest, 'No chunkmanifest found'
pkl_name = manifest[0].name.removesuffix('.chunkmanifest')
num_chunks = int(manifest[0].read_text().strip())
chunks = []
for i in range(num_chunks):
chunk = dm_dir / f'{pkl_name}.chunk{i+1:02d}of{num_chunks:02d}'
chunks.append({
'file_name': chunk.name,
'sha256': hashlib.sha256(chunk.read_bytes()).hexdigest()
})
digest = hashlib.sha256()
for c in chunks:
with open(dm_dir / c['file_name'], 'rb') as f:
while block := f.read(1024*1024):
digest.update(block)
metadata = {
'bundles': [{
'short_name': 'DMMODEL',
'display_name': '${{ needs.resolve.outputs.model_name }}',
'ref': '${{ needs.resolve.outputs.onnx_ref }}',
'runner': 'tinygrad',
'build_time': datetime.now(UTC).strftime('%Y-%m-%dT%H:%M:%SZ'),
'models': [{
'type': 'chunked',
'artifact': {
'file_name': pkl_name,
'download_uri': {'url': '', 'sha256': digest.hexdigest()},
'chunks': chunks
}
}]
}]
}
with open(dm_dir / 'metadata.json', 'w') as f:
json.dump(metadata, f, indent=2)
print('Generated DM metadata.json')
"
python3 release/ci/upload_default_model.py \
--hf-repo "${{ env.HF_REPO }}" \
--hf-defaults-path "${{ needs.resolve.outputs.hf_defaults_path }}" \
--artifact-name "dm-model-${{ github.run_number }}" \
--model-dir dm_output \
--onnx-path "${{ needs.resolve.outputs.onnx_path }}" \
--onnx-ref "${{ needs.resolve.outputs.onnx_ref }}" \
--model-name "${{ needs.resolve.outputs.model_name }}" \
--tinygrad-ref "${{ needs.resolve.outputs.tinygrad_ref }}" \
--run-number "${{ github.run_number }}"
build_dm_model:
needs: resolve
if: ${{ inputs.target == 'dm' }}
runs-on: [self-hosted, tici]
env:
DM_ONNX: openpilot/selfdrive/modeld/models/dmonitoring_model.onnx
DM_PKL: openpilot/selfdrive/modeld/models/dmonitoring_model_tinygrad.pkl
steps:
- uses: actions/checkout@v4
with:
submodules: recursive
- name: Pull DM ONNX via LFS
run: git lfs pull -I "${{ env.DM_ONNX }}"
- name: Set environment variables
run: |
source /etc/profile
export UV_PROJECT_ENVIRONMENT=${HOME}/venv
export UV_PYTHON_PREFERENCE=managed
export UV_PYTHON_INSTALL_DIR=${HOME}/uv/python
export VIRTUAL_ENV=$UV_PROJECT_ENVIRONMENT
uv sync --frozen
printenv >> $GITHUB_ENV
- name: Disable powersave
run: |
source ${UV_PROJECT_ENVIRONMENT}/bin/activate
PYTHONPATH=$PYTHONPATH:${{ github.workspace }}/ ${{ github.workspace }}/scripts/manage-powersave.py --disable
- name: Compile DM model
run: |
source ${UV_PROJECT_ENVIRONMENT}/bin/activate
export PYTHONPATH="${PYTHONPATH}:${{ github.workspace }}/tinygrad_repo:${{ github.workspace }}"
TG_FLAGS="DEV=QCOM IMAGE=1 FLOAT16=1 NOLOCALS=1 JIT_BATCH_SIZE=0 OPENPILOT_HACKS=1"
taskset -c 7 env ${TG_FLAGS} python3 \
${{ github.workspace }}/tinygrad_repo/examples/openpilot/compile3.py \
${{ github.workspace }}/${{ env.DM_ONNX }} \
${{ github.workspace }}/${{ env.DM_PKL }}
- name: Chunk DM pkl
run: |
source ${UV_PROJECT_ENVIRONMENT}/bin/activate
export PYTHONPATH=${{ github.workspace }}
python3 -c "
from openpilot.common.file_chunker import chunk_file, get_chunk_targets
import os
pkl = '${{ github.workspace }}/${{ env.DM_PKL }}'
size = os.path.getsize(pkl)
targets = get_chunk_targets(pkl, size)
chunk_file(pkl, targets)
print(f'Chunked {pkl} into {len(targets)} chunks')
"
- name: Prepare DM output
run: |
mkdir -p dm_output
cp ${{ github.workspace }}/${{ env.DM_PKL }}.chunk* dm_output/
cp ${{ github.workspace }}/${{ env.DM_PKL }}.chunkmanifest dm_output/
- name: Upload DM artifact
uses: actions/upload-artifact@v4
with:
name: dm-model-${{ github.run_number }}
path: dm_output/
- name: Re-enable powersave
if: always()
run: |
source ${UV_PROJECT_ENVIRONMENT}/bin/activate
PYTHONPATH=$PYTHONPATH:${{ github.workspace }}/ ${{ github.workspace }}/scripts/manage-powersave.py --enable