Compare commits

...

3 Commits

Author SHA1 Message Date
Jason Wen 5ae100aa1d models fetcher: bump big model to v21 2026-08-20 19:19:59 -04:00
Jason Wen be76a88b80 ci override LFS fetch exclude for real ONNX file retrieval (#1928)
ci: override lfs.fetchexclude so the model fetch pulls real ONNX files instead of pointers
2026-08-20 19:12:59 -04:00
James Vecellio-Grant 049d225d5a ci: Dedicated Model Runner (#1922)
* ci: Dedicated Model Runner

* recurse

* not needed

* fix wrapper

* whoops

* bypass

* modeld_v2: restore chestnut link check before big model build

* modeld_v2: stage onnx to disk instead of shared memory

* ci: clear unchunked onnx temps before model build

* ci: stream the pkl hash instead of loading it into memory

---------

Co-authored-by: Jason Wen <haibin.wen3@gmail.com>
2026-08-20 16:18:17 -04:00
5 changed files with 96 additions and 40 deletions
+34 -16
View File
@@ -103,20 +103,25 @@ jobs:
- run: | - run: |
cd ${{ github.workspace }}/openpilot/openpilot cd ${{ github.workspace }}/openpilot/openpilot
if [ "${{ inputs.target_hardware }}" != "usbgpu" ]; then if [ "${{ inputs.target_hardware }}" != "usbgpu" ]; then
git lfs pull -X "selfdrive/modeld/models/big_*.onnx" -X "selfdrive/modeld/models/dmonitoring_*.onnx" git lfs pull -X "**/selfdrive/modeld/models/big_*.onnx,**/selfdrive/modeld/models/dmonitoring_*.onnx"
rm -f selfdrive/modeld/models/big_*.onnx selfdrive/modeld/models/dmonitoring_*.onnx rm -f selfdrive/modeld/models/big_*.onnx selfdrive/modeld/models/dmonitoring_*.onnx
else else
git lfs pull -I "selfdrive/modeld/models/big_*.onnx" git lfs pull -I "**/selfdrive/modeld/models/big_*.onnx" -X ""
find selfdrive/modeld/models -name "*.onnx" ! -name "big_*.onnx" -delete find selfdrive/modeld/models -name "*.onnx" ! -name "big_*.onnx" -delete
fi fi
if grep -lIF "version https://git-lfs.github.com/spec/v1" selfdrive/modeld/models/*.onnx; then
echo "::error::the ONNX files above are still LFS pointers, not real models"
exit 1
fi
- name: 'Upload Artifact' - name: 'Upload Artifact'
uses: actions/upload-artifact@v4 uses: actions/upload-artifact@v4
with: with:
name: models-${{ env.REF }}${{ inputs.artifact_suffix }} name: models-${{ env.REF }}${{ inputs.artifact_suffix }}
path: ${{ github.workspace }}/openpilot/openpilot/selfdrive/modeld/models/*.onnx path: ${{ github.workspace }}/openpilot/openpilot/selfdrive/modeld/models/*.onnx
if-no-files-found: error
build_model: build_model:
runs-on: [self-hosted, tici] runs-on: [self-hosted, usbgpu]
needs: get_model needs: get_model
env: env:
MODEL_NAME: ${{ inputs.custom_name || inputs.upstream_branch }} (${{ needs.get_model.outputs.model_date }}) MODEL_NAME: ${{ inputs.custom_name || inputs.upstream_branch }} (${{ needs.get_model.outputs.model_date }})
@@ -127,7 +132,6 @@ jobs:
fetch-depth: 1 fetch-depth: 1
submodules: recursive submodules: recursive
- run: git lfs pull
- name: Set environment variables - name: Set environment variables
id: set-env id: set-env
@@ -160,7 +164,7 @@ jobs:
fi fi
source ${UV_PROJECT_ENVIRONMENT}/bin/activate source ${UV_PROJECT_ENVIRONMENT}/bin/activate
PYTHONPATH=$PYTHONPATH:${{ github.workspace }}/ ${{ github.workspace }}/scripts/manage-powersave.py --disable PYTHONPATH=$PYTHONPATH:${{ github.workspace }}/ ${{ github.workspace }}/scripts/manage-powersave.py --disable
rm -rf ${{ env.MODELS_DIR }}/*.onnx rm -rf ${{ env.MODELS_DIR }}/*.onnx*
- name: Download model artifacts - name: Download model artifacts
uses: actions/download-artifact@v4 uses: actions/download-artifact@v4
@@ -180,6 +184,7 @@ jobs:
MODEL_SIZE=$(python3 -c "from openpilot.common.transformations.model import MEDMODEL_INPUT_SIZE as s; print(f'{s[0]}x{s[1]}')") 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}')") CAMERA_RES=$(python3 -c "from openpilot.common.transformations.camera import _ar_ox_fisheye as a, _os_fisheye as o; print(f'{a.width}x{a.height} {o.width}x{o.height}')")
TG_FLAGS_QCOM="DEV=QCOM IMAGE=1 FLOAT16=1 NOLOCALS=1 JIT_BATCH_SIZE=0 OPENPILOT_HACKS=1"
if [ "${{ inputs.target_hardware }}" == "usbgpu" ]; then if [ "${{ inputs.target_hardware }}" == "usbgpu" ]; then
echo "USBGPU build" echo "USBGPU build"
export USBGPU=1 export USBGPU=1
@@ -187,27 +192,40 @@ jobs:
OUTPUT_PKL="${{ env.MODELS_DIR }}/big_driving_tinygrad.pkl" OUTPUT_PKL="${{ env.MODELS_DIR }}/big_driving_tinygrad.pkl"
else else
echo "QCOM build" echo "QCOM build"
TG_FLAGS="DEV=QCOM IMAGE=1 FLOAT16=1 NOLOCALS=1 JIT_BATCH_SIZE=0 OPENPILOT_HACKS=1" TG_FLAGS="$TG_FLAGS_QCOM"
OUTPUT_PKL="${{ env.MODELS_DIR }}/driving_tinygrad.pkl" OUTPUT_PKL="${{ env.MODELS_DIR }}/driving_tinygrad.pkl"
fi fi
# Generate metadata for all ONNX files # Generate metadata for all ONNX files
find "${{ env.MODELS_DIR }}" -maxdepth 1 -name '*.onnx' | while IFS= read -r onnx_file; do find "${{ env.MODELS_DIR }}" -maxdepth 1 -name '*.onnx' | while IFS= read -r onnx_file; do
echo "Generating metadata: $onnx_file" echo "Generating metadata: $onnx_file"
env ${TG_FLAGS} python3 "${{ env.MODELS_DIR }}/../get_model_metadata.py" "$onnx_file" || true env ${TG_FLAGS_QCOM} python3 "${{ env.MODELS_DIR }}/../get_model_metadata.py" "$onnx_file" || true
done done
# Detect model type and build compile args # Detect model type and build compile args
VISION_ONNX="${{ env.MODELS_DIR }}/driving_vision.onnx" VISION_ONNX=""
POLICY_ONNX="${{ env.MODELS_DIR }}/driving_policy.onnx" for f in "${{ env.MODELS_DIR }}/driving_vision.onnx" "${{ env.MODELS_DIR }}/big_driving_vision.onnx"; do
OFF_POLICY_ONNX="${{ env.MODELS_DIR }}/driving_off_policy.onnx" [ -f "$f" ] && VISION_ONNX="$f" && break
ON_POLICY_ONNX="${{ env.MODELS_DIR }}/driving_on_policy.onnx" done
POLICY_ONNX=""
for f in "${{ env.MODELS_DIR }}/driving_policy.onnx" "${{ env.MODELS_DIR }}/big_driving_policy.onnx"; do
[ -f "$f" ] && POLICY_ONNX="$f" && break
done
OFF_POLICY_ONNX=""
for f in "${{ env.MODELS_DIR }}/driving_off_policy.onnx" "${{ env.MODELS_DIR }}/big_driving_off_policy.onnx"; do
[ -f "$f" ] && OFF_POLICY_ONNX="$f" && break
done
ON_POLICY_ONNX=""
for f in "${{ env.MODELS_DIR }}/driving_on_policy.onnx" "${{ env.MODELS_DIR }}/big_driving_on_policy.onnx"; do
[ -f "$f" ] && ON_POLICY_ONNX="$f" && break
done
SUPERCOMBO_ONNX="" SUPERCOMBO_ONNX=""
for f in "${{ env.MODELS_DIR }}/supercombo.onnx" "${{ env.MODELS_DIR }}/driving_supercombo.onnx"; do for f in "${{ env.MODELS_DIR }}/supercombo.onnx" "${{ env.MODELS_DIR }}/driving_supercombo.onnx" "${{ env.MODELS_DIR }}/big_supercombo.onnx" "${{ env.MODELS_DIR }}/big_driving_supercombo.onnx"; do
if [ -f "$f" ]; then [ -f "$f" ] && SUPERCOMBO_ONNX="$f" && break
SUPERCOMBO_ONNX="$f"
break
fi
done done
MODEL_TYPE="" ONNX_ARGS="" OUTPUT_NAME="" MODEL_TYPE="" ONNX_ARGS="" OUTPUT_NAME=""
@@ -272,18 +272,17 @@ def _parse_size(size_str: str) -> tuple[int, int]:
return int(width), int(height) return int(width), int(height)
def read_file_chunked_to_shm(path): def read_file_chunked_to_disk(path):
if not path: if not path:
return None return None
import atexit import atexit
import shutil import shutil
from openpilot.common.file_chunker import open_file_chunked from openpilot.common.file_chunker import open_file_chunked
from openpilot.common.hardware.hw import Paths tmp_path = f'{path}.unchunked'
shm_path = os.path.join(Paths.shm_path(), os.path.basename(path)) with open(tmp_path, 'wb') as f, open_file_chunked(path) as src:
atexit.register(lambda: os.path.exists(shm_path) and os.remove(shm_path)) shutil.copyfileobj(src, f)
with open(shm_path, 'wb') as dst, open_file_chunked(path) as src: atexit.register(lambda: os.path.exists(tmp_path) and os.remove(tmp_path))
shutil.copyfileobj(src, dst) return tmp_path
return shm_path
def _load_policy_runners(args: argparse.Namespace) -> tuple[list, list]: def _load_policy_runners(args: argparse.Namespace) -> tuple[list, list]:
@@ -327,11 +326,11 @@ if __name__ == "__main__":
model_w, model_h = args.model_size model_w, model_h = args.model_size
output_data = {} output_data = {}
args.vision_onnx = read_file_chunked_to_shm(args.vision_onnx) args.vision_onnx = read_file_chunked_to_disk(args.vision_onnx)
args.policy_onnx = read_file_chunked_to_shm(args.policy_onnx) args.policy_onnx = read_file_chunked_to_disk(args.policy_onnx)
args.off_policy_onnx = read_file_chunked_to_shm(args.off_policy_onnx) args.off_policy_onnx = read_file_chunked_to_disk(args.off_policy_onnx)
args.on_policy_onnx = read_file_chunked_to_shm(args.on_policy_onnx) args.on_policy_onnx = read_file_chunked_to_disk(args.on_policy_onnx)
args.supercombo_onnx = read_file_chunked_to_shm(args.supercombo_onnx) args.supercombo_onnx = read_file_chunked_to_disk(args.supercombo_onnx)
vision_runner = OnnxRunner(args.vision_onnx) if args.vision_onnx else None vision_runner = OnnxRunner(args.vision_onnx) if args.vision_onnx else None
@@ -5,10 +5,15 @@ This file is part of sunnypilot and is licensed under the MIT License.
See the LICENSE.md file in the root directory for more details. See the LICENSE.md file in the root directory for more details.
""" """
import os
import tempfile
from pathlib import Path
import numpy as np import numpy as np
from openpilot.common.parameterized import parameterized from openpilot.common.parameterized import parameterized
from openpilot.sunnypilot.modeld_v2.compile_modeld import derive_frame_skip, _detect_desire_key from openpilot.common.file_chunker import chunk_file, get_chunk_targets
from openpilot.sunnypilot.modeld_v2.compile_modeld import derive_frame_skip, _detect_desire_key, read_file_chunked_to_disk
from openpilot.common.test import OpenpilotTestCase from openpilot.common.test import OpenpilotTestCase
@@ -160,3 +165,33 @@ class TestOutputSlicePreservation(OpenpilotTestCase):
policy_slices = {'plan': slice(0, 495), 'meta': slice(495, 550)} policy_slices = {'plan': slice(0, 495), 'meta': slice(495, 550)}
assert set(vision_slices.keys()) & set(policy_slices.keys()) == set(), \ assert set(vision_slices.keys()) & set(policy_slices.keys()) == set(), \
"vision and policy slices should not overlap in keys" "vision and policy slices should not overlap in keys"
class TestReadFileChunkedToDisk(OpenpilotTestCase):
def test_none_passthrough(self):
assert read_file_chunked_to_disk(None) is None
def test_unchunked_source_staged_on_disk(self):
with tempfile.TemporaryDirectory() as d:
src = Path(d) / "driving_supercombo.onnx"
payload = os.urandom(1024)
src.write_bytes(payload)
out = Path(read_file_chunked_to_disk(str(src)))
assert out.parent == Path(d)
assert out.name == "driving_supercombo.onnx.unchunked"
assert out.read_bytes() == payload
def test_chunked_source_reassembled_on_disk(self):
with tempfile.TemporaryDirectory() as d:
src = Path(d) / "driving_supercombo.onnx"
payload = os.urandom(4096)
src.write_bytes(payload)
chunk_file(str(src), get_chunk_targets(str(src), len(payload)))
assert not src.exists()
out = Path(read_file_chunked_to_disk(str(src)))
assert out.parent == Path(d)
assert out.read_bytes() == payload
+1 -1
View File
@@ -141,7 +141,7 @@ class ModelCache:
class ModelFetcher: class ModelFetcher:
"""Handles fetching and caching of model data from remote source""" """Handles fetching and caching of model data from remote source"""
MODEL_URL = "https://raw.githubusercontent.com/sunnypilot/sunnypilot-models/refs/heads/gh-pages/docs/driving_models_v20.json" MODEL_URL = "https://raw.githubusercontent.com/sunnypilot/sunnypilot-models/refs/heads/gh-pages/docs/driving_models_v20.json"
MODEL_URL_USBGPU = "https://raw.githubusercontent.com/sunnypilot/sunnypilot-models/refs/heads/gh-pages/docs/driving_models_usbgpu_v20.json" MODEL_URL_USBGPU = "https://raw.githubusercontent.com/sunnypilot/sunnypilot-models/refs/heads/gh-pages/docs/driving_models_usbgpu_v21.json"
def __init__(self, params: Params): def __init__(self, params: Params):
self.params = params self.params = params
+14 -10
View File
@@ -53,24 +53,28 @@ def create_pkl_name(full_name: str) -> str:
return pkl return pkl
def _read_pkl_bytes(pkl_path: Path) -> bytes: def _hash_pkl(pkl_path: Path) -> str:
manifest = Path(f"{pkl_path}.chunkmanifest") manifest = Path(f"{pkl_path}.chunkmanifest")
if manifest.exists(): if manifest.exists():
num_chunks = int(manifest.read_text().strip()) num_chunks = int(manifest.read_text().strip())
parts = [] paths = [Path(f"{pkl_path}.chunk{i + 1:02d}of{num_chunks:02d}") for i in range(num_chunks)]
for i in range(num_chunks): else:
chunk = Path(f"{pkl_path}.chunk{i + 1:02d}of{num_chunks:02d}") paths = [pkl_path]
parts.append(chunk.read_bytes())
return b''.join(parts) digest = hashlib.sha256()
return pkl_path.read_bytes() for path in paths:
with path.open('rb') as f:
while block := f.read(1024 * 1024):
digest.update(block)
return digest.hexdigest()
def _find_driving_pkl(output_path: Path) -> Path | None: def _find_driving_pkl(output_path: Path) -> Path | None:
for pattern in ('driving_tinygrad.pkl', 'driving_*_tinygrad.pkl'): for pattern in ('*driving_tinygrad.pkl', '*driving_*_tinygrad.pkl'):
matches = sorted(output_path.glob(pattern)) matches = sorted(output_path.glob(pattern))
if matches: if matches:
return matches[0] return matches[0]
for pattern in ('driving_tinygrad.pkl.chunkmanifest', 'driving_*_tinygrad.pkl.chunkmanifest'): for pattern in ('*driving_tinygrad.pkl.chunkmanifest', '*driving_*_tinygrad.pkl.chunkmanifest'):
matches = sorted(output_path.glob(pattern)) matches = sorted(output_path.glob(pattern))
if matches: if matches:
return Path(str(matches[0]).removesuffix('.chunkmanifest')) return Path(str(matches[0]).removesuffix('.chunkmanifest'))
@@ -87,7 +91,7 @@ def _rename_pkl_with_chunks(old_pkl: Path, new_pkl: Path) -> Path:
def generate_chunked_model(driving_pkl: Path) -> dict: def generate_chunked_model(driving_pkl: Path) -> dict:
tinygrad_hash = hashlib.sha256(_read_pkl_bytes(driving_pkl)).hexdigest() tinygrad_hash = _hash_pkl(driving_pkl)
chunks_config = [] chunks_config = []
manifest_file = Path(f"{driving_pkl}.chunkmanifest") manifest_file = Path(f"{driving_pkl}.chunkmanifest")