models: persist model selection per catalog across chestnut state changes (#1960)

* models: preserve user model selection across reboots and power cycles

* no

* again

* idk

* over

.github/workflows/build-default-big-model.yaml

@@ -1,83 +0,0 @@
-name: Build default big model
-
-on:
-  workflow_dispatch:
-
-env:
-  HF_REPO: sunnypilot/sunnypilot_models_v1
-  HF_DEFAULTS_PATH: models/defaults/big
-
-jobs:
-  resolve_name:
-    runs-on: ubuntu-24.04
-    outputs:
-      model_name: ${{ steps.name.outputs.model_name }}
-      onnx_ref: ${{ steps.name.outputs.onnx_ref }}
-    steps:
-      - uses: actions/checkout@v4
-      - id: name
-        run: |
-          NAME=$(PYTHONPATH=${{ github.workspace }} python3 -c "from openpilot.sunnypilot.models.model_name import DEFAULT_BIG_MODEL; print(DEFAULT_BIG_MODEL)")
-          ONNX_REF=$(git log -1 --format='%H' -- openpilot/selfdrive/modeld/models/big_driving_supercombo.onnx)
-          echo "model_name=${NAME}" >> $GITHUB_OUTPUT
-          echo "onnx_ref=$ONNX_REF" >> $GITHUB_OUTPUT
-
-  build_model:
-    needs: resolve_name
-    uses: ./.github/workflows/sunnypilot-build-model.yaml
-    with:
-      upstream_branch: ${{ needs.resolve_name.outputs.onnx_ref }}
-      custom_name: ${{ needs.resolve_name.outputs.model_name }}
-      target_hardware: usbgpu
-    secrets: inherit
-
-  upload_defaults:
-    needs: [ resolve_name, build_model ]
-    runs-on: ubuntu-24.04
-    permissions:
-      id-token: write
-      contents: write
-    steps:
-      - uses: actions/checkout@v4
-        with:
-          submodules: recursive
-      - run: git lfs pull -I "openpilot/selfdrive/modeld/models/big_driving_supercombo.onnx"
-
-      - name: Install huggingface_hub
-        run: pip install --upgrade "huggingface_hub>=0.22.0"
-
-      - name: Download artifact name
-        uses: actions/download-artifact@v4
-        with:
-          name: artifact-name-${{ needs.resolve_name.outputs.model_name }}
-          path: artifact_name
-
-      - name: Read artifact name
-        id: artifact
-        run: |
-          ARTIFACT_NAME=$(cat artifact_name/artifact_name.txt)
-          echo "artifact_name=$ARTIFACT_NAME" >> $GITHUB_OUTPUT
-
-      - name: Download model artifact
-        uses: actions/download-artifact@v4
-        with:
-          name: ${{ steps.artifact.outputs.artifact_name }}
-          path: output
-
-      - name: Upload to HF and update default_models.json
-        env:
-          HF_OIDC_RESOURCE: datasets/${{ 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 "${{ env.HF_REPO }}" \
-            --hf-defaults-path "${{ env.HF_DEFAULTS_PATH }}" \
-            --artifact-name "$ARTIFACT_NAME" \
-            --model-dir output \
-            --onnx-path "openpilot/selfdrive/modeld/models/big_driving_supercombo.onnx" \
-            --onnx-ref "${{ needs.resolve_name.outputs.onnx_ref }}" \
-            --model-name "${{ needs.resolve_name.outputs.model_name }}" \
-            --tinygrad-ref "$(python3 openpilot/sunnypilot/models/tinygrad_ref.py)" \
-            --run-number "${{ github.run_number }}"

.github/workflows/build-default-models.yaml

@@ -0,0 +1,501 @@
+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
+

.github/workflows/download-hf-model-chunks/action.yml

@@ -0,0 +1,66 @@
+name: Download HF model chunks
+description: Resolve and download model chunks from HuggingFace in parallel
+
+inputs:
+  hf_repo:
+    description: HuggingFace dataset repo
+    required: true
+  models:
+    description: 'JSON array of {hf_path, onnx_hash, canonical} objects'
+    required: true
+  dest_dir:
+    description: Destination directory for downloaded chunks
+    required: true
+
+runs:
+  using: composite
+  steps:
+    - name: Download model chunks
+      shell: bash
+      env:
+        HF_REPO: ${{ inputs.hf_repo }}
+        MODELS_JSON: ${{ inputs.models }}
+        DEST_DIR: ${{ inputs.dest_dir }}
+      run: |
+        set -eo pipefail
+        DOWNLOAD_LIST=$(mktemp)
+
+        resolve_chunks() {
+          local HF_PATH="$1" ONNX_HASH="$2" CANONICAL="$3" DEST_DIR="$4"
+          local JSON_URL="https://huggingface.co/datasets/${HF_REPO}/resolve/main/${HF_PATH}/default_models.json"
+          local DEFAULTS BUNDLE ARTIFACT BASE_URL NUM_CHUNKS
+          DEFAULTS=$(curl -fsSL "$JSON_URL")
+          BUNDLE=$(echo "$DEFAULTS" | jq --arg hash "$ONNX_HASH" '.bundles[] | select(.onnx_sha256 == $hash)')
+          ARTIFACT=$(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')
+
+          mkdir -p "$DEST_DIR"
+          while IFS= read -r CHUNK_NAME; do
+            CHUNK_IDX=$(echo "$CHUNK_NAME" | grep -oP 'chunk\K[0-9]+of[0-9]+' || true)
+            if [ -z "$CHUNK_IDX" ]; then
+              echo "::error::Failed to parse chunk index from: $CHUNK_NAME"
+              return 1
+            fi
+            ENCODED_URL=$(python3 -c "import urllib.parse; print(urllib.parse.quote('${BASE_URL}/${CHUNK_NAME}', safe=':/'))")
+            printf '%s\t%s\n' "$ENCODED_URL" "${DEST_DIR}/${CANONICAL}.chunk${CHUNK_IDX}" >> "$DOWNLOAD_LIST"
+          done < <(echo "$ARTIFACT" | jq -r '.chunks[].file_name')
+          echo "$NUM_CHUNKS" > "${DEST_DIR}/${CANONICAL}.chunkmanifest"
+        }
+
+        echo "$MODELS_JSON" | jq -c '.[]' | while IFS= read -r model; do
+          HF_PATH=$(echo "$model" | jq -r '.hf_path')
+          ONNX_HASH=$(echo "$model" | jq -r '.onnx_hash')
+          CANONICAL=$(echo "$model" | jq -r '.canonical')
+          resolve_chunks "$HF_PATH" "$ONNX_HASH" "$CANONICAL" "$DEST_DIR"
+        done
+
+        TOTAL=$(wc -l < "$DOWNLOAD_LIST")
+        echo "Downloading $TOTAL chunks with 8 parallel connections..."
+        xargs -P8 -d'\n' -I{} bash -c '
+          URL="${1%%	*}"
+          DEST="${1#*	}"
+          echo "Downloading $(basename "$DEST")"
+          curl -fsSL --retry 3 --retry-delay 5 -o "$DEST" "$URL"
+        ' _ {} < "$DOWNLOAD_LIST"
+        rm -f "$DOWNLOAD_LIST"

.github/workflows/sunnypilot-build-model.yaml

@@ -188,7 +188,7 @@ jobs:
           if [ "${{ inputs.target_hardware }}" == "usbgpu" ]; then
             echo "USBGPU build"
             export USBGPU=1
-            TG_FLAGS="DEBUG=2 DEV=USB+AMD:LLVM WARP_DEV=QCOM FLOAT16=1 JIT_BATCH_SIZE=0 GMMU=0 TC_OPT=2"
+            TG_FLAGS="DEBUG=1 DEV=USB+AMD:LLVM WARP_DEV=QCOM FLOAT16=1 JIT_BATCH_SIZE=0 GMMU=0 TC_OPT=2"
             OUTPUT_PKL="${{ env.MODELS_DIR }}/big_driving_tinygrad.pkl"
           else
             echo "QCOM build"

.github/workflows/sunnypilot-build-prebuilt.yaml

@@ -39,6 +39,8 @@ jobs:
       include_big_model: ${{ steps.strategy.outputs.include_big_model }}
     steps:
       - uses: actions/checkout@v4
+        with:
+          fetch-depth: 1
       - name: Extract deploy strategy
         id: strategy
         run: |
@@ -96,6 +98,8 @@ jobs:
       }}
     steps:
       - uses: actions/checkout@v4
+        with:
+          fetch-depth: 1
       - name: Wait for Tests
         uses: ./.github/workflows/wait-for-action # Path to where you place the action
         with:
@@ -119,6 +123,7 @@ jobs:
     steps:
       - uses: actions/checkout@v4
         with:
+          fetch-depth: 1
           submodules: recursive
           ref: ${{ env.SOURCE_BRANCH }}
           repository: ${{ github.event.pull_request.head.repo.fork && github.event.pull_request.head.repo.full_name || github.repository }}
@@ -165,7 +170,7 @@ jobs:
           scons -j1 cache_dir="$SCONS_CACHE" --minimal \
             openpilot/selfdrive/locationd openpilot/sunnypilot/selfdrive/locationd
           echo "Building rest of sunnypilot"
-          /usr/bin/time -v scons -j$(nproc) cache_dir="$SCONS_CACHE" --minimal
+          SKIP_TINYGRAD_COMPILE=1 /usr/bin/time -v scons -j$(nproc) cache_dir="$SCONS_CACHE" --minimal
           touch ${BUILD_DIR}/prebuilt
           if [[ "${{ runner.debug }}" == "1" ]]; then
             ls -la ${BUILD_DIR}
@@ -214,59 +219,174 @@ jobs:
     outputs:
       onnx_sha256: ${{ steps.resolve.outputs.onnx_sha256 }}
     env:
+      GH_REPO: ${{ github.repository }}
       HF_REPO: sunnypilot/sunnypilot_models_v1
       HF_DEFAULTS_PATH: models/defaults/big
     steps:
-      - uses: actions/checkout@v4
-        with:
-          ref: ${{ github.head_ref || github.ref_name }}
-
-      - run: git lfs pull -I "openpilot/selfdrive/modeld/models/big_driving_supercombo.onnx"
-
-      - name: Check HF defaults and build if needed
+      - name: Resolve ONNX hash and tinygrad ref via API
         id: resolve
         run: |
-          ACTUAL_ONNX_HASH=$(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" >> $GITHUB_OUTPUT
+          REF="${{ github.head_ref || github.ref_name }}"
+
+          ONNX_HASH=$(gh api "repos/${GH_REPO}/contents/openpilot/selfdrive/modeld/models/big_driving_supercombo.onnx?ref=${REF}" --jq '.content' | base64 -d | grep '^oid sha256:' | cut -d: -f2)
+          echo "ONNX hash: $ONNX_HASH"
+          echo "onnx_sha256=$ONNX_HASH" >> $GITHUB_OUTPUT
+
+          TINYGRAD_REF=$(gh api "repos/${GH_REPO}/contents/tinygrad_repo?ref=${REF}" --jq '.sha')
+          echo "tinygrad ref: $TINYGRAD_REF"
 
           JSON_URL="https://huggingface.co/datasets/${HF_REPO}/resolve/main/${HF_DEFAULTS_PATH}/default_models.json"
 
-          check_hash() {
+          check_defaults() {
             DEFAULTS=$(curl -fsSL "$JSON_URL" 2>/dev/null) || return 1
-            BUNDLE=$(echo "$DEFAULTS" | jq --arg hash "$ACTUAL_ONNX_HASH" '.bundles[] | select(.onnx_sha256 == $hash)' 2>/dev/null)
+            TINYGRAD_MATCH=$(echo "$DEFAULTS" | jq -r --arg ref "$TINYGRAD_REF" '.tinygrad_ref == $ref' 2>/dev/null)
+            [ "$TINYGRAD_MATCH" = "true" ] || return 1
+            BUNDLE=$(echo "$DEFAULTS" | jq --arg hash "$ONNX_HASH" '.bundles[] | select(.onnx_sha256 == $hash)' 2>/dev/null)
             [ -n "$BUNDLE" ] && [ "$BUNDLE" != "null" ]
           }
 
-          if check_hash; then
-            echo "HF defaults match repo ONNX"
-          else
-            echo "No matching model on HF — triggering build"
-            gh workflow run build-default-big-model.yaml --ref "${{ github.head_ref || github.ref_name }}"
-
-            echo "Waiting for build to start..."
-            sleep 120
-
-            RUN_ID=$(gh run list --workflow=build-default-big-model.yaml --branch="${{ github.head_ref || github.ref_name }}" --limit=1 --json databaseId --jq '.[0].databaseId')
-            if [ -z "$RUN_ID" ] || [ "$RUN_ID" = "null" ]; then
-              echo "::error::Failed to find build-default-big-model run"
-              exit 1
-            fi
-
-            echo "Waiting for run $RUN_ID..."
-            gh run watch "$RUN_ID"
-
-            CONCLUSION=$(gh run view "$RUN_ID" --json conclusion --jq '.conclusion')
-            if [ "$CONCLUSION" != "success" ]; then
-              echo "::error::build-default-big-model failed: $CONCLUSION"
-              exit 1
-            fi
-
-            if ! check_hash; then
-              echo "::error::HF defaults still don't match after build"
-              exit 1
-            fi
+          if check_defaults; then
+            echo "HF defaults match repo ONNX hash and tinygrad ref"
+            exit 0
           fi
+
+          echo "No matching model on HF — dispatching build"
+          gh workflow run build-default-models.yaml --ref "$REF" -f target=big
+
+          echo "Polling HF for big model availability..."
+          for i in $(seq 1 90); do
+            sleep 30
+            if check_defaults; then
+              echo "Big model available on HF after $((i * 30))s"
+              exit 0
+            fi
+            echo "Poll $i/90: not yet available"
+          done
+
+          echo "::error::Big model not available on HF after 45 minutes"
+          exit 1
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Cancel run on failure
+        if: failure()
+        run: gh run cancel ${{ github.run_id }}
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+
+  prepare_small_model:
+    needs: [ prepare_strategy ]
+    runs-on: ubuntu-24.04
+    outputs:
+      driving_onnx_sha256: ${{ steps.resolve.outputs.driving_onnx_sha256 }}
+    env:
+      GH_REPO: ${{ github.repository }}
+      HF_REPO: sunnypilot/sunnypilot_models_v1
+      HF_DEFAULTS_PATH: models/defaults/small
+    steps:
+      - name: Resolve ONNX hash and tinygrad ref via API
+        id: resolve
+        run: |
+          REF="${{ github.head_ref || github.ref_name }}"
+
+          DRIVING_HASH=$(gh api "repos/${GH_REPO}/contents/openpilot/selfdrive/modeld/models/driving_supercombo.onnx?ref=${REF}" --jq '.content' | base64 -d | grep '^oid sha256:' | cut -d: -f2)
+          echo "Driving ONNX hash: $DRIVING_HASH"
+          echo "driving_onnx_sha256=$DRIVING_HASH" >> $GITHUB_OUTPUT
+
+          TINYGRAD_REF=$(gh api "repos/${GH_REPO}/contents/tinygrad_repo?ref=${REF}" --jq '.sha')
+          echo "tinygrad ref: $TINYGRAD_REF"
+
+          JSON_URL="https://huggingface.co/datasets/${HF_REPO}/resolve/main/${HF_DEFAULTS_PATH}/default_models.json"
+
+          check_defaults() {
+            DEFAULTS=$(curl -fsSL "$JSON_URL" 2>/dev/null) || return 1
+            TINYGRAD_MATCH=$(echo "$DEFAULTS" | jq -r --arg ref "$TINYGRAD_REF" '.tinygrad_ref == $ref' 2>/dev/null)
+            [ "$TINYGRAD_MATCH" = "true" ] || return 1
+            DRIVING=$(echo "$DEFAULTS" | jq --arg hash "$DRIVING_HASH" '.bundles[] | select(.onnx_sha256 == $hash)' 2>/dev/null)
+            [ -n "$DRIVING" ] && [ "$DRIVING" != "null" ] || return 1
+          }
+
+          if check_defaults; then
+            echo "HF defaults match repo ONNX hash and tinygrad ref"
+            exit 0
+          fi
+
+          echo "No matching model on HF — dispatching build"
+          gh workflow run build-default-models.yaml --ref "$REF" -f target=small
+
+          echo "Polling HF for model availability..."
+          for i in $(seq 1 60); do
+            sleep 30
+            if check_defaults; then
+              echo "Model available on HF after $((i * 30))s"
+              exit 0
+            fi
+            echo "Poll $i/60: not yet available"
+          done
+
+          echo "::error::Small driving model not available on HF after 30 minutes"
+          exit 1
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Cancel run on failure
+        if: failure()
+        run: gh run cancel ${{ github.run_id }}
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+
+  prepare_dm_model:
+    needs: [ prepare_strategy ]
+    runs-on: ubuntu-24.04
+    outputs:
+      dm_onnx_sha256: ${{ steps.resolve.outputs.dm_onnx_sha256 }}
+    env:
+      GH_REPO: ${{ github.repository }}
+      HF_REPO: sunnypilot/sunnypilot_models_v1
+      HF_DEFAULTS_PATH: models/defaults/dm
+    steps:
+      - name: Resolve ONNX hash and tinygrad ref via API
+        id: resolve
+        run: |
+          REF="${{ github.head_ref || github.ref_name }}"
+
+          DM_HASH=$(gh api "repos/${GH_REPO}/contents/openpilot/selfdrive/modeld/models/dmonitoring_model.onnx?ref=${REF}" --jq '.content' | base64 -d | grep '^oid sha256:' | cut -d: -f2)
+          echo "DM ONNX hash: $DM_HASH"
+          echo "dm_onnx_sha256=$DM_HASH" >> $GITHUB_OUTPUT
+
+          TINYGRAD_REF=$(gh api "repos/${GH_REPO}/contents/tinygrad_repo?ref=${REF}" --jq '.sha')
+          echo "tinygrad ref: $TINYGRAD_REF"
+
+          JSON_URL="https://huggingface.co/datasets/${HF_REPO}/resolve/main/${HF_DEFAULTS_PATH}/default_models.json"
+
+          check_defaults() {
+            DEFAULTS=$(curl -fsSL "$JSON_URL" 2>/dev/null) || return 1
+            TINYGRAD_MATCH=$(echo "$DEFAULTS" | jq -r --arg ref "$TINYGRAD_REF" '.tinygrad_ref == $ref' 2>/dev/null)
+            [ "$TINYGRAD_MATCH" = "true" ] || return 1
+            DM=$(echo "$DEFAULTS" | jq --arg hash "$DM_HASH" '.bundles[] | select(.onnx_sha256 == $hash)' 2>/dev/null)
+            [ -n "$DM" ] && [ "$DM" != "null" ] || return 1
+          }
+
+          if check_defaults; then
+            echo "HF defaults match DM ONNX hash and tinygrad ref"
+            exit 0
+          fi
+
+          echo "No matching DM model on HF — dispatching build"
+          gh workflow run build-default-models.yaml --ref "$REF" -f target=dm
+
+          echo "Polling HF for DM model availability..."
+          for i in $(seq 1 60); do
+            sleep 30
+            if check_defaults; then
+              echo "DM model available on HF after $((i * 30))s"
+              exit 0
+            fi
+            echo "Poll $i/60: not yet available"
+          done
+
+          echo "::error::DM model not available on HF after 30 minutes"
+          exit 1
         env:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
 
@@ -278,23 +398,24 @@ jobs:
 
   publish:
     concurrency:
-      # We do a bit of a hack here to avoid canceling the publishing job if a new commit comes in while we're publishing by adding the sha to the group name.
-      # This means that if multiple commits come in while we're publishing, they will be queued up and publish one after the other.
-      # Otherwise, if a job is waiting to be published due to environment wait time, it would be canceled by a new commit and restart the wait time.
       group: ${{ needs.prepare_strategy.outputs.publish_concurrency_group }}
       cancel-in-progress: ${{ needs.prepare_strategy.outputs.cancel_publish_in_progress == 'true' }}
     if: ${{
       always() && !cancelled() &&
       needs.build.result == 'success' &&
       needs.prepare_strategy.result == 'success' &&
+      needs.prepare_small_model.result == 'success' &&
+      needs.prepare_dm_model.result == 'success' &&
       (!contains(github.event_name, 'pull_request') || (github.event.action == 'labeled' && github.event.label.name == 'prebuilt')) &&
       (needs.prepare_strategy.outputs.include_big_model != 'true' || needs.prepare_chestnut.result == 'success')
       }}
-    needs: [ build, prepare_strategy, prepare_chestnut ]
+    needs: [ build, prepare_strategy, prepare_chestnut, prepare_small_model, prepare_dm_model ]
     runs-on: ubuntu-24.04
     environment: ${{ needs.prepare_strategy.outputs.environment }}
     steps:
       - uses: actions/checkout@v4
+        with:
+          fetch-depth: 1
 
       - name: Download prebuilt artifact
         uses: actions/download-artifact@v4
@@ -306,43 +427,16 @@ jobs:
           mkdir -p ${{ env.OUTPUT_DIR }}
           tar xzf prebuilt.tar.gz -C ${{ env.OUTPUT_DIR }}
 
-      - name: Prepare chestnut output
-        if: ${{ needs.prepare_chestnut.result == 'success' }}
-        run: |
-          mkdir -p "${{ github.workspace }}/chestnut_output"
-          tar xzf prebuilt.tar.gz -C "${{ github.workspace }}/chestnut_output"
-
-      - name: Download big model chunks from HF
-        if: ${{ needs.prepare_chestnut.result == 'success' }}
-        env:
-          HF_REPO: sunnypilot/sunnypilot_models_v1
-          HF_DEFAULTS_PATH: models/defaults/big
-        run: |
-          ONNX_HASH="${{ 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: ${{ needs.prepare_chestnut.result == 'success' }}
-        run: |
-          cp big_model_chunks/* "${{ github.workspace }}/chestnut_output/openpilot/selfdrive/modeld/models/"
+      - name: Download model chunks from HF
+        uses: ./.github/workflows/download-hf-model-chunks
+        with:
+          hf_repo: sunnypilot/sunnypilot_models_v1
+          dest_dir: ${{ env.OUTPUT_DIR }}/openpilot/selfdrive/modeld/models
+          models: |
+            [
+              {"hf_path": "models/defaults/small", "onnx_hash": "${{ needs.prepare_small_model.outputs.driving_onnx_sha256 }}", "canonical": "driving_tinygrad.pkl"},
+              {"hf_path": "models/defaults/dm", "onnx_hash": "${{ needs.prepare_dm_model.outputs.dm_onnx_sha256 }}", "canonical": "dmonitoring_model_tinygrad.pkl"}
+            ]
 
       - name: Configure Git
         run: |
@@ -364,22 +458,6 @@ jobs:
             "https://x-access-token:${{github.token}}@github.com/sunnypilot/sunnypilot.git" \
             "${{ needs.prepare_strategy.outputs.extra_version_identifier }}"
 
-      - name: Publish chestnut branch
-        if: ${{ needs.prepare_chestnut.result == 'success' }}
-        env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-        run: |
-          CHESTNUT_BRANCH="${{ needs.prepare_strategy.outputs.new_branch }}-chestnut"
-          CHESTNUT_DIR="${{ github.workspace }}/chestnut_output"
-
-          ${{ env.CI_DIR }}/publish.sh \
-            "${{ github.workspace }}" \
-            "$CHESTNUT_DIR" \
-            "$CHESTNUT_BRANCH" \
-            "${{ needs.prepare_strategy.outputs.version }}" \
-            "https://x-access-token:${{github.token}}@github.com/sunnypilot/sunnypilot.git" \
-            "${{ needs.prepare_strategy.outputs.extra_version_identifier }}"
-
       - name: Tag ${{ needs.prepare_strategy.outputs.environment }}
         if: ${{ needs.prepare_strategy.outputs.is_stable_branch == 'true' && (github.event_name != 'push' || !startsWith(github.ref, 'refs/tags/')) }}
         run: |
@@ -387,12 +465,77 @@ jobs:
             git tag -f -a ${TAG} -m "${{ needs.prepare_strategy.outputs.environment }} @ ${{ needs.prepare_strategy.outputs.version }} of build ${{ needs.prepare_strategy.outputs.build }}."
             git push -f origin ${TAG}
 
+  publish_chestnut:
+    concurrency:
+      group: ${{ needs.prepare_strategy.outputs.publish_concurrency_group }}-chestnut
+      cancel-in-progress: ${{ needs.prepare_strategy.outputs.cancel_publish_in_progress == 'true' }}
+    if: ${{
+      always() && !cancelled() &&
+      needs.build.result == 'success' &&
+      needs.prepare_strategy.result == 'success' &&
+      needs.prepare_small_model.result == 'success' &&
+      needs.prepare_dm_model.result == 'success' &&
+      needs.prepare_chestnut.result == 'success' &&
+      (!contains(github.event_name, 'pull_request') || (github.event.action == 'labeled' && github.event.label.name == 'prebuilt'))
+      }}
+    needs: [ build, prepare_strategy, prepare_chestnut, prepare_small_model, prepare_dm_model ]
+    runs-on: ubuntu-24.04
+    environment: ${{ needs.prepare_strategy.outputs.environment }}
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          fetch-depth: 1
+
+      - name: Download prebuilt artifact
+        uses: actions/download-artifact@v4
+        with:
+          name: prebuilt
+
+      - name: Untar prebuilt
+        run: |
+          mkdir -p ${{ env.OUTPUT_DIR }}
+          tar xzf prebuilt.tar.gz -C ${{ env.OUTPUT_DIR }}
+
+      - name: Download model chunks from HF
+        uses: ./.github/workflows/download-hf-model-chunks
+        with:
+          hf_repo: sunnypilot/sunnypilot_models_v1
+          dest_dir: ${{ env.OUTPUT_DIR }}/openpilot/selfdrive/modeld/models
+          models: |
+            [
+              {"hf_path": "models/defaults/small", "onnx_hash": "${{ needs.prepare_small_model.outputs.driving_onnx_sha256 }}", "canonical": "driving_tinygrad.pkl"},
+              {"hf_path": "models/defaults/dm", "onnx_hash": "${{ needs.prepare_dm_model.outputs.dm_onnx_sha256 }}", "canonical": "dmonitoring_model_tinygrad.pkl"},
+              {"hf_path": "models/defaults/big", "onnx_hash": "${{ needs.prepare_chestnut.outputs.onnx_sha256 }}", "canonical": "big_driving_tinygrad.pkl"}
+            ]
+
+      - name: Configure Git
+        run: |
+          git config --global user.email "github-actions[bot]@users.noreply.github.com"
+          git config --global user.name "github-actions[bot]"
+
+      - name: Publish chestnut branch
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        run: |
+          CHESTNUT_BRANCH="${{ needs.prepare_strategy.outputs.new_branch }}-chestnut"
+
+          ${{ env.CI_DIR }}/publish.sh \
+            "${{ github.workspace }}" \
+            "${{ env.OUTPUT_DIR }}" \
+            "$CHESTNUT_BRANCH" \
+            "${{ needs.prepare_strategy.outputs.version }}" \
+            "https://x-access-token:${{github.token}}@github.com/sunnypilot/sunnypilot.git" \
+            "${{ needs.prepare_strategy.outputs.extra_version_identifier }}"
+
   notify:
     needs:
     - prepare_strategy
     - build
     - publish
+    - publish_chestnut
     - prepare_chestnut
+    - prepare_small_model
+    - prepare_dm_model
     runs-on: ubuntu-24.04
     if: ${{ (always() && !cancelled() && !failure())
       && needs.publish.result == 'success'
@@ -400,6 +543,8 @@ jobs:
       && (fromJSON(vars.DEV_FEEDBACK_NOTIFICATION_BRANCHES_V2)[github.head_ref || github.ref_name] != null) }}
     steps:
       - uses: actions/checkout@v4
+        with:
+          fetch-depth: 1
 
       - name: Prepare notification message
         id: message

openpilot/common/params_keys.h

@@ -196,6 +196,8 @@ inline static std::unordered_map<std::string, ParamKeyAttributes> keys = {
     // Model Manager params
     {"ModelManager_ActiveBundle", {PERSISTENT, JSON}},
     {"ModelManager_ActiveJson", {CLEAR_ON_MANAGER_START, STRING}},
+    {"ModelManager_PrevBundle", {PERSISTENT, JSON}},
+    {"ModelManager_PrevBundle_USBGPU", {PERSISTENT, JSON}},
     {"ModelManager_ClearCache", {CLEAR_ON_MANAGER_START, BOOL}},
     {"ModelManager_DownloadIndex", {CLEAR_ON_MANAGER_START | CLEAR_ON_ONROAD_TRANSITION, INT}},
     {"ModelManager_Favs", {PERSISTENT | BACKUP, STRING}},

openpilot/selfdrive/modeld/SConscript

@@ -73,44 +73,45 @@ compile_modeld_script = [
 model_w, model_h = MEDMODEL_INPUT_SIZE
 frame_skip = ModelConstants.MODEL_RUN_FREQ // ModelConstants.MODEL_CONTEXT_FREQ
 
-for usbgpu in [False, True] if USBGPU else [False]:
-  target_pkl_path = File(modeld_pkl_path(usbgpu)).abspath
-  # BIG_INTO_SMALL=1 builds the default target from the big model, e.g. to test it without a USB GPU
-  file_prefix, cmd_flags = ('big_', usbgpu_tg_flags) if usbgpu else ('big_' if os.getenv('BIG_INTO_SMALL') else '', tg_flags)
-  driving_onnx_deps = get_existing_chunks(File(f"models/{file_prefix}driving_supercombo.onnx").abspath)
-  camera_res_args = ' '.join(f'{cw}x{ch}' for cw, ch in CAMERA_CONFIGS)
-  # CPU 7 is isolated with isolcpus on AGNOS, so explicitly pin the compiler to it.
-  taskset = 'taskset -c 7 ' if arch == 'comma_arm64' else ''
-  cmd = (f'{cmd_flags} {mac_brew_string} {taskset}python3 {modeld_dir}/compile_modeld.py '
-        f'--model-size {model_w}x{model_h} '
-        f'--camera-resolutions {camera_res_args} '
-        f'--onnx {File(f"models/{file_prefix}driving_supercombo.onnx").abspath} '
-        f'--output {target_pkl_path} --frame-skip {frame_skip}')
-  onnx_sizes_sum = sum(os.path.getsize(f) for f in driving_onnx_deps)
-  chunk_targets = get_chunk_targets(target_pkl_path, estimate_pickle_max_size(onnx_sizes_sum))
-  def do_compile(target, source, env, command=cmd, pkl=target_pkl_path, chunks=chunk_targets):
-    from openpilot.system.hardware.chestnut.flash import link_up
-    # chestnut can enumerate before its PCIe link is up due to varying 12V power behavior across cars
-    for _ in range(10):
-      if link_up():
-        break
-      time.sleep(1)
-    else:
-      print("Chestnut not ready, skipping big model build")
-      return
-    if ret := env.Execute(command):
-      return ret
-    chunk_file(pkl, chunks)
-  def do_chunk(target, source, env, pkl=target_pkl_path, chunks=chunk_targets):
-    chunk_file(pkl, chunks)
-  actions = Action(do_compile, "  [USBGPU] $TARGET") if usbgpu else [cmd, Action(do_chunk, "  [CHUNK] $TARGET")]
-  node = lenv.Command(
-    chunk_targets,
-    tinygrad_files + compile_modeld_script + driving_onnx_deps + [Value(chunk_targets), chunker_file],
-    actions,
-  )
-  if usbgpu:
-    lenv.SideEffect(usbgpu_lock, node)
+if not os.getenv('SKIP_TINYGRAD_COMPILE'):
+  for usbgpu in [False, True] if USBGPU else [False]:
+    target_pkl_path = File(modeld_pkl_path(usbgpu)).abspath
+    # BIG_INTO_SMALL=1 builds the default target from the big model, e.g. to test it without a USB GPU
+    file_prefix, cmd_flags = ('big_', usbgpu_tg_flags) if usbgpu else ('big_' if os.getenv('BIG_INTO_SMALL') else '', tg_flags)
+    driving_onnx_deps = get_existing_chunks(File(f"models/{file_prefix}driving_supercombo.onnx").abspath)
+    camera_res_args = ' '.join(f'{cw}x{ch}' for cw, ch in CAMERA_CONFIGS)
+    # CPU 7 is isolated with isolcpus on AGNOS, so explicitly pin the compiler to it.
+    taskset = 'taskset -c 7 ' if arch == 'comma_arm64' else ''
+    cmd = (f'{cmd_flags} {mac_brew_string} {taskset}python3 {modeld_dir}/compile_modeld.py '
+          f'--model-size {model_w}x{model_h} '
+          f'--camera-resolutions {camera_res_args} '
+          f'--onnx {File(f"models/{file_prefix}driving_supercombo.onnx").abspath} '
+          f'--output {target_pkl_path} --frame-skip {frame_skip}')
+    onnx_sizes_sum = sum(os.path.getsize(f) for f in driving_onnx_deps)
+    chunk_targets = get_chunk_targets(target_pkl_path, estimate_pickle_max_size(onnx_sizes_sum))
+    def do_compile(target, source, env, command=cmd, pkl=target_pkl_path, chunks=chunk_targets):
+      from openpilot.system.hardware.chestnut.flash import link_up
+      # chestnut can enumerate before its PCIe link is up due to varying 12V power behavior across cars
+      for _ in range(10):
+        if link_up():
+          break
+        time.sleep(1)
+      else:
+        print("Chestnut not ready, skipping big model build")
+        return
+      if ret := env.Execute(command):
+        return ret
+      chunk_file(pkl, chunks)
+    def do_chunk(target, source, env, pkl=target_pkl_path, chunks=chunk_targets):
+      chunk_file(pkl, chunks)
+    actions = Action(do_compile, "  [USBGPU] $TARGET") if usbgpu else [cmd, Action(do_chunk, "  [CHUNK] $TARGET")]
+    node = lenv.Command(
+      chunk_targets,
+      tinygrad_files + compile_modeld_script + driving_onnx_deps + [Value(chunk_targets), chunker_file],
+      actions,
+    )
+    if usbgpu:
+      lenv.SideEffect(usbgpu_lock, node)
 
 # get model metadata
 fn = File(f"models/dmonitoring_model").abspath
@@ -142,4 +143,5 @@ def tg_compile(flags, model_name):
      Action(do_chunk, "  [CHUNK] $TARGET")],
   )
 
-tg_compile(tg_flags, 'dmonitoring_model')
+if not os.getenv('SKIP_TINYGRAD_COMPILE'):
+  tg_compile(tg_flags, 'dmonitoring_model')

openpilot/selfdrive/ui/sunnypilot/layouts/settings/models.py

@@ -115,8 +115,12 @@ class ModelsLayout(Widget):
   def calculate_cache_size():
     cache_size = 0.0
     if os.path.exists(CUSTOM_MODEL_PATH):
-      cache_size = sum(os.path.getsize(os.path.join(CUSTOM_MODEL_PATH, file)) for file in os.listdir(CUSTOM_MODEL_PATH)) / (1024**2)
-    return cache_size
+      for file in os.listdir(CUSTOM_MODEL_PATH):
+        try:
+          cache_size += os.path.getsize(os.path.join(CUSTOM_MODEL_PATH, file))
+        except OSError:
+          continue
+    return cache_size / (1024**2)
 
   def _clear_cache(self):
     def _callback(response):

openpilot/sunnypilot/modeld_v2/compile_modeld.py

@@ -7,6 +7,7 @@ See the LICENSE.md file in the root directory for more details.
 """
 
 import argparse
+import math
 import os
 import tempfile
 import time
@@ -66,14 +67,15 @@ def get_policy_npy_shapes(input_shapes: dict, is_supercombo: bool = False) -> tu
   if desire_key:
     shapes['desire'] = (input_shapes[desire_key][2],)
 
-  if is_supercombo and 'features_buffer' in input_shapes:
-    fb = input_shapes['features_buffer']
-    shapes['prev_feat'] = (fb[0], fb[2])
-
   for key, shape in input_shapes.items():
     if key not in (desire_key, 'features_buffer') and 'img' not in key:
       shapes[key] = tuple(shape)
 
+  if is_supercombo and 'features_buffer' in input_shapes:
+    fb = input_shapes['features_buffer']
+    feat_dim = math.prod(fb[2:])
+    shapes['prev_feat'] = (fb[0], feat_dim)
+
   sizes = [int(np.prod(size)) for size in shapes.values()]
   return shapes, sizes
 
@@ -117,8 +119,9 @@ def generate_queues_and_npy(input_shapes: dict, frame_skip: int, device: str = D
   }
 
   if features_buffer:
+    feat_dim = math.prod(features_buffer[2:])
     feat_q_len = frame_skip * features_buffer[1] if is_supercombo else frame_skip * (features_buffer[1] - 1) + 1
-    queues['feat_q'] = Tensor(np.zeros((feat_q_len, features_buffer[0], features_buffer[2]),
+    queues['feat_q'] = Tensor(np.zeros((feat_q_len, features_buffer[0], feat_dim),
                        dtype=np.float32), device=device).contiguous().realize()
 
   queues.update({key: Tensor(value, device='NPY').realize() for key, value in npy_arrays.items() if key in ('tfm', 'big_tfm')})
@@ -183,14 +186,14 @@ def make_run_policy(vision_runner, policy_runners: list, features_slice: slice,
     warped_dev = warped.to(Device.DEFAULT)
     Tensor.realize(packed_npy_inputs_dev, warped_dev)
 
-    img = shift_and_sample(img_q, warped_dev[0:1], sample_skip_fn).realize()
-    big_img = shift_and_sample(big_img_q, warped_dev[1:2], sample_skip_fn).realize()
+    img = shift_and_sample(img_q, warped_dev[0:1], sample_skip_fn)
+    big_img = shift_and_sample(big_img_q, warped_dev[1:2], sample_skip_fn)
 
     unpacked_tensors = [tensor.reshape(shape) for tensor, shape in zip(packed_npy_inputs_dev.split(npy_sizes), npy_shapes.values(), strict=True)]
     unpacked_dict = dict(zip(npy_shapes.keys(), unpacked_tensors, strict=True))
 
     desire_dev = unpacked_dict['desire']
-    desire_buf = shift_and_sample(desire_q, desire_dev.reshape(1, 1, -1), sample_desire_fn).realize()
+    desire_buf = shift_and_sample(desire_q, desire_dev.reshape(1, 1, -1), sample_desire_fn)
 
     inputs = {desire_key: desire_buf}
     for key, tensor_val in unpacked_dict.items():
@@ -199,7 +202,7 @@ def make_run_policy(vision_runner, policy_runners: list, features_slice: slice,
 
     if 'prev_feat' in unpacked_dict:
       prev_feat_dev = unpacked_dict['prev_feat']
-      inputs['features_buffer'] = shift_and_sample(feat_q, prev_feat_dev.reshape(1, 1, -1), sample_skip_fn).realize()
+      inputs['features_buffer'] = shift_and_sample(feat_q, prev_feat_dev.reshape(1, 1, -1), sample_skip_fn).reshape(input_shapes['features_buffer'])
 
     if vision_runner:
       vision_out_cast = next(iter(vision_runner({road_key: img, wide_key: big_img}).values())).cast('float32').realize()
@@ -211,7 +214,7 @@ def make_run_policy(vision_runner, policy_runners: list, features_slice: slice,
 
     inputs.update({road_key: img, wide_key: big_img})
     if 'features_buffer' not in inputs:
-      inputs['features_buffer'] = sample_skip_fn(feat_q)
+      inputs['features_buffer'] = sample_skip_fn(feat_q).reshape(input_shapes['features_buffer'])
 
     policy_out = next(iter(policy_runners[0](inputs).values())).cast('float32').realize()
     if 'features_buffer' not in inputs and features_slice is not None:

openpilot/sunnypilot/modeld_v2/tests/test_compile_modeld.py

@@ -195,3 +195,85 @@ class TestReadFileChunkedToDisk(OpenpilotTestCase):
 
       assert out.parent == Path(d)
       assert out.read_bytes() == payload
+
+
+class Test4DFeaturesBuffer(OpenpilotTestCase):
+  def test_get_policy_npy_shapes_4d(self):
+    from openpilot.sunnypilot.modeld_v2.compile_modeld import get_policy_npy_shapes
+    input_shapes = {
+      'desire_pulse': (1, 25, 8),
+      'features_buffer': (1, 24, 32, 512),  # compare 4d to 3d for regression
+      'traffic_convention': (1, 2),
+      'action_t': (1, 2)
+    }
+    shapes, sizes = get_policy_npy_shapes(input_shapes, is_supercombo=True)
+    assert shapes['prev_feat'] == (1, 16384)
+    assert sizes == [8, 2, 2, 16384]
+
+  def test_get_policy_npy_shapes_3d(self):
+    from openpilot.sunnypilot.modeld_v2.compile_modeld import get_policy_npy_shapes
+    input_shapes = {
+      'desire_pulse': (1, 25, 8),
+      'features_buffer': (1, 24, 512),
+      'traffic_convention': (1, 2),
+      'action_t': (1, 2)
+    }
+    shapes, sizes = get_policy_npy_shapes(input_shapes, is_supercombo=True)
+    assert shapes['prev_feat'] == (1, 512)
+    assert sizes == [8, 2, 2, 512]
+
+
+class TestStockCompileModeldEquivalence(OpenpilotTestCase):
+  def test_get_policy_npy_shapes_matches_stock(self):
+    from openpilot.selfdrive.modeld.compile_modeld import get_policy_npy_shapes as stock_get_policy_npy_shapes
+    from openpilot.sunnypilot.modeld_v2.compile_modeld import get_policy_npy_shapes as sunny_get_policy_npy_shapes
+
+    stock_input_shapes = {
+      'desire_pulse': (1, 25, 8),
+      'features_buffer': (1, 24, 512), # see below comment
+      'traffic_convention': (1, 2),
+      'action_t': (1, 2),
+    }
+
+    stock_shapes, stock_sizes = stock_get_policy_npy_shapes(stock_input_shapes)
+    sunny_shapes, sunny_sizes = sunny_get_policy_npy_shapes(stock_input_shapes, is_supercombo=True)
+
+    assert sunny_shapes == stock_shapes
+    assert sunny_sizes == stock_sizes
+    assert sunny_shapes['prev_feat'] == (1, 512)
+
+  def test_make_input_queues_full_stock_equivalence(self):
+    from openpilot.selfdrive.modeld.compile_modeld import make_input_queues as stock_make_input_queues
+    from openpilot.sunnypilot.modeld_v2.compile_modeld import make_supercombo_input_queues as sunny_make_supercombo_input_queues
+    input_shapes = {
+      'img': (1, 12, 128, 256),
+      'desire_pulse': (1, 25, 8),
+      'features_buffer': (1, 24, 512),  # when https://github.com/commaai/openpilot/pull/38681 merges, update to 1,24,32,512
+      'traffic_convention': (1, 2),
+      'action_t': (1, 2),
+    }
+    frame_skip = 4
+
+    stock_queues, stock_npy = stock_make_input_queues(input_shapes, frame_skip, device='NPY')
+    sunny_queues, sunny_npy = sunny_make_supercombo_input_queues(input_shapes, frame_skip, device='NPY')
+    assert set(sunny_queues.keys()) == set(stock_queues.keys())
+    for key in stock_queues:
+      assert sunny_queues[key].shape == stock_queues[key].shape, \
+        f"Queue shape mismatch for {key}: sunny {sunny_queues[key].shape} != stock {stock_queues[key].shape}"
+    assert set(sunny_npy.keys()) == set(stock_npy.keys())
+    for key in stock_npy:
+      assert sunny_npy[key].shape == stock_npy[key].shape, \
+        f"Numpy array shape mismatch for {key}: sunny {sunny_npy[key].shape} != stock {stock_npy[key].shape}"
+
+  def test_make_warp_queues_stock_equivalence(self):
+    from openpilot.selfdrive.modeld.compile_modeld import make_warp_input_queues as stock_make_warp_queues
+    from openpilot.sunnypilot.modeld_v2.compile_modeld import make_warp_queues as sunny_make_warp_queues
+    stock_vision_shapes = {'img': (1, 12, 128, 256)}  # for now?
+    stock_queues, stock_npy = stock_make_warp_queues(stock_vision_shapes, frame_skip=4, device='NPY')
+    sunny_queues, sunny_npy = sunny_make_warp_queues(device='NPY')
+
+    assert set(sunny_npy.keys()) == set(stock_npy.keys()) == {'tfm', 'big_tfm'}
+    for key in sunny_npy:
+      assert sunny_npy[key].shape == stock_npy[key].shape == (3, 3)
+
+

openpilot/sunnypilot/models/fetcher.py

@@ -13,8 +13,6 @@ from openpilot.common.params import Params
 from openpilot.common.swaglog import cloudlog
 from openpilot.common.hardware.hw import Paths
 from openpilot.sunnypilot.models.helpers import is_bundle_version_compatible
-from openpilot.selfdrive.modeld.helpers import usbgpu_present
-
 from openpilot.cereal import custom
 
 
@@ -140,8 +138,8 @@ class ModelCache:
 
 class ModelFetcher:
   """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_USBGPU = "https://raw.githubusercontent.com/sunnypilot/sunnypilot-models/refs/heads/gh-pages/docs/driving_models_usbgpu_v21.json"
+  MODEL_URL = "https://raw.githubusercontent.com/sunnypilot/sunnypilot-models/refs/heads/gh-pages/docs/driving_models_v21.json"
+  MODEL_URL_USBGPU = "https://raw.githubusercontent.com/sunnypilot/sunnypilot-models/refs/heads/gh-pages/docs/driving_models_usbgpu_v22.json"
 
   def __init__(self, params: Params):
     self.params = params
@@ -149,11 +147,10 @@ class ModelFetcher:
     self._is_usbgpu: bool | None = None
     self.model_cache = ModelCache(params)
     self.model_url = self.MODEL_URL
-    self._update_model_source()
 
-  def _update_model_source(self) -> None:
-    """Updates what json to use based on usbgpu availability"""
-    is_usbgpu = usbgpu_present()
+  def _update_model_source(self, chestnut_present: bool) -> None:
+    """Updates what json to use based on chestnut hardware presence via deviceState"""
+    is_usbgpu = chestnut_present
     if is_usbgpu != self._is_usbgpu:
       self._is_usbgpu = is_usbgpu
       self.model_cache = ModelCache(self.params, suffix="_USBGPU" if is_usbgpu else "")
@@ -191,9 +188,9 @@ class ModelFetcher:
 
     return None
 
-  def get_available_bundles(self) -> list[custom.ModelManagerSP.ModelBundle]:
+  def get_available_bundles(self, chestnut_present: bool = False) -> list[custom.ModelManagerSP.ModelBundle]:
     """Gets the list of available models, with smart cache handling"""
-    self._update_model_source()
+    self._update_model_source(chestnut_present)
     cached_data, is_expired = self.model_cache.get()
 
     if cached_data and not is_expired:
@@ -210,10 +207,12 @@ class ModelFetcher:
     cloudlog.warning("Failed to fetch fresh data. Using expired cache as fallback")
     return self.model_parser.parse_models(cached_data)
 
+
 if __name__ == "__main__":
+  from openpilot.selfdrive.modeld.helpers import usbgpu_present
   params = Params()
   model_fetcher = ModelFetcher(params)
-  bundles = model_fetcher.get_available_bundles()
+  bundles = model_fetcher.get_available_bundles(chestnut_present=usbgpu_present())
   for bundle in bundles:
     for model in bundle.models:
       model_overrides = {override.key: override.value for override in bundle.overrides}

openpilot/sunnypilot/models/helpers.py

@@ -18,12 +18,11 @@ from openpilot.sunnypilot.models.constants import Meta, MetaSimPose, MetaTombRai
 from openpilot.common.hardware.hw import Paths
 
 # SET ME TO THE EXACT JSON VERSION WE SET IN SUNNYPILOT_MODELS REPO
-REQUIRED_JSON_VERSION = 17
+REQUIRED_JSON_VERSION = 18
 
 CUSTOM_MODEL_PATH = Paths.model_root()
 METADATA_PATH = Path(__file__).parent / '../models/supercombo_metadata.pkl'
 ModelManager = custom.ModelManagerSP
-_LAST_VALIDATED_RAW = None
 
 
 def _compute_hash(file_path: str) -> str | None:
@@ -86,11 +85,11 @@ def _bundle_needs_reset(active_bundle: custom.ModelManagerSP.ModelBundle, availa
   if available_bundles is not None:
     matching_bundle = None
     for bundle in available_bundles:
-      if getattr(active_bundle, 'ref', None) and getattr(bundle, 'ref', None):
+      if active_bundle.ref and bundle.ref:
         if active_bundle.ref == bundle.ref:
           matching_bundle = bundle
           break
-      elif getattr(active_bundle, 'internalName', None) == getattr(bundle, 'internalName', None):
+      elif active_bundle.internalName == bundle.internalName:
         matching_bundle = bundle
         break
 
@@ -98,36 +97,42 @@ def _bundle_needs_reset(active_bundle: custom.ModelManagerSP.ModelBundle, availa
       return True
     if active_bundle.minimumSelectorVersion != matching_bundle.minimumSelectorVersion:
       return True
-
-    active_runner = getattr(active_bundle, 'runner', None)
-    matching_runner = getattr(matching_bundle, 'runner', None)
-    if active_runner is not None and matching_runner is not None:
-      if getattr(active_runner, 'raw', active_runner) != getattr(matching_runner, 'raw', matching_runner):
-        return True
+    if active_bundle.runner.raw != matching_bundle.runner.raw:
+      return True
     if set(_bundle_artifacts(active_bundle)) != set(_bundle_artifacts(matching_bundle)):
       return True
 
-  return not _bundle_is_valid_locally(active_bundle)
+  # missing files trigger re-download, not selection reset
+  return False
 
 
-def validate_active_bundle(params: Params, available_bundles: list[custom.ModelManagerSP.ModelBundle] | None = None) -> None:
-  global _LAST_VALIDATED_RAW
+def _prev_bundle_key(is_usbgpu: bool) -> str:
+  return "ModelManager_PrevBundle_USBGPU" if is_usbgpu else "ModelManager_PrevBundle"
 
+
+def validate_active_bundle(params: Params, available_bundles: list[custom.ModelManagerSP.ModelBundle] | None = None,
+                           is_usbgpu: bool = False) -> None:
   raw_bundle = params.get("ModelManager_ActiveBundle")
   if not raw_bundle:
-    return
-
-  if raw_bundle == _LAST_VALIDATED_RAW:
+    prev = params.get(_prev_bundle_key(is_usbgpu))
+    if prev and (prev_bundle := get_active_bundle(params, raw_bundle_dict=prev)) is not None:
+      if not _bundle_needs_reset(prev_bundle, available_bundles):
+        params.put("ModelManager_ActiveBundle", prev, block=True)
     return
 
   active_bundle = get_active_bundle(params, raw_bundle_dict=raw_bundle)
   if active_bundle is None or _bundle_needs_reset(active_bundle, available_bundles):
     cloudlog.warning("Active model bundle invalid; resetting to default")
+    params.put(_prev_bundle_key(not is_usbgpu), raw_bundle, block=True)
+
+    prev = params.get(_prev_bundle_key(is_usbgpu))
+    if prev and (prev_bundle := get_active_bundle(params, raw_bundle_dict=prev)) is not None:
+      if not _bundle_needs_reset(prev_bundle, available_bundles):
+        params.put("ModelManager_ActiveBundle", prev, block=True)
+        return
+
     params.remove("ModelManager_ActiveBundle")
     params.put("ModelRunnerTypeCache", int(custom.ModelManagerSP.Runner.stock), block=True)
-    _LAST_VALIDATED_RAW = None
-  else:
-    _LAST_VALIDATED_RAW = raw_bundle
 
 
 def get_active_bundle(params: Params | None = None, raw_bundle_dict: dict | bytes | None = None) -> "custom.ModelManagerSP.ModelBundle | None":

openpilot/sunnypilot/models/manager.py

@@ -30,6 +30,7 @@ class ModelManagerSP:
     self.params = Params()
     self.model_fetcher = ModelFetcher(self.params)
     self.pm = messaging.PubMaster(["modelManagerSP"])
+    self.sm = messaging.SubMaster(["deviceState"])
     self.available_models: list[custom.ModelManagerSP.ModelBundle] = []
     self.selected_bundle: custom.ModelManagerSP.ModelBundle = None
     self.active_bundle: custom.ModelManagerSP.ModelBundle = get_active_bundle(self.params)
@@ -256,14 +257,21 @@ class ModelManagerSP:
     """Main entry point for downloading a model bundle"""
     asyncio.run(self._download_bundle(model_bundle, destination_path))
 
+  BOOT_SETTLE_TICKS = 10  # seconds at 1 Hz before validating active bundle
+
   def main_thread(self) -> None:
     """Main thread for model management"""
     rk = Ratekeeper(1, print_delay_threshold=None)
+    boot_ticks = 0
 
     while True:
       try:
-        self.available_models = self.model_fetcher.get_available_bundles()
-        validate_active_bundle(self.params, self.available_models)
+        self.sm.update(0)
+        chestnut_present = self.sm['deviceState'].chestnutPresent
+        self.available_models = self.model_fetcher.get_available_bundles(chestnut_present)
+        if boot_ticks >= self.BOOT_SETTLE_TICKS:
+          validate_active_bundle(self.params, self.available_models, is_usbgpu=chestnut_present)
+        boot_ticks = min(boot_ticks + 1, self.BOOT_SETTLE_TICKS)
         self.active_bundle = get_active_bundle(self.params)
 
         if (index_to_download := self.params.get("ModelManager_DownloadIndex")) is not None:

openpilot/sunnypilot/sunnylink/athena/sunnylinkd.py

@@ -28,7 +28,6 @@ from websocket import (ABNF, WebSocket, WebSocketException, WebSocketTimeoutExce
                        create_connection, WebSocketConnectionClosedException)
 
 import openpilot.cereal.messaging as messaging
-from openpilot.selfdrive.modeld.helpers import usbgpu_present
 from openpilot.sunnypilot.models.model_name import DEFAULT_MODEL, DEFAULT_BIG_MODEL
 from openpilot.sunnypilot.selfdrive.car.sync_sunnylink_params import update_car_list_param
 from openpilot.sunnypilot.sunnylink.api import SunnylinkApi
@@ -182,10 +181,8 @@ def getParamsMetadata() -> str:
     schema = generate_schema()
     schema["capabilities"] = generate_capabilities()
     schema["capability_labels"] = CAPABILITY_LABELS
-    # mirrors get_default_model() — ui_state unavailable in sunnylinkd process
-    show_big = (usbgpu_present()
-                and (params.get_bool("UsbGpuActive") or params.get_bool("UsbGpuLoading") or params.get_bool("IsOffroad")))
-    schema["default_model"] = DEFAULT_BIG_MODEL if show_big else DEFAULT_MODEL
+    schema["default_model"] = DEFAULT_MODEL
+    schema["default_big_model"] = DEFAULT_BIG_MODEL
     schema["usbgpu_active"] = params.get_bool("UsbGpuActive")
     raw = json.dumps(schema, separators=(",", ":")).encode("utf-8")
     return base64.b64encode(gzip.compress(raw)).decode("utf-8")

release/ci/model_generator.py

@@ -136,7 +136,7 @@ def generate_chunked_model(driving_pkl: Path) -> dict:
 
 
 def create_metadata_json(models: list, output_dir: Path, custom_name=None, short_name=None, is_20hz=False, upstream_branch="unknown",
-                         onnx_sha256=None) -> None:
+                         onnx_sha256=None, is_big=False) -> None:
   bundle_json = {
     "short_name": short_name,
     "display_name": custom_name or upstream_branch,
@@ -149,6 +149,7 @@ def create_metadata_json(models: list, output_dir: Path, custom_name=None, short
     "generation": "-1",
     "build_time": datetime.now(UTC).strftime("%Y-%m-%dT%H:%M:%SZ"),
     "overrides": {},
+    "is_big": is_big,
     "models": models,
   }
 
@@ -186,6 +187,8 @@ if __name__ == "__main__":
     print(f"No driving_tinygrad.pkl found in {_output_dir}", file=sys.stderr)
     sys.exit(1)
 
+  is_big = _driving_pkl.name.startswith('big_')
+
   if _pkl:
     new_pkl = _output_dir / f"driving_{_pkl}_tinygrad.pkl"
     if not new_pkl.exists():
@@ -196,4 +199,4 @@ if __name__ == "__main__":
   _model_metadata = generate_chunked_model(_driving_pkl)
   _onnx_sha256 = _hash_onnx_files(Path(args.model_dir))
   create_metadata_json([_model_metadata], _output_dir, args.custom_name, _short_name, args.is_20hz, args.upstream_branch,
-                       onnx_sha256=_onnx_sha256)
+                       onnx_sha256=_onnx_sha256, is_big=is_big)

release/ci/publish.sh

@@ -47,7 +47,7 @@ git rm -rf $OUTPUT_DIR/.git || true # Doing cleanup, but it might fail if the .g
 git remote remove origin || true # ensure cleanup
 git remote add origin $GIT_ORIGIN
 #git push origin -d $DEV_BRANCH || true # Ensuring we delete the remote branch if it exists as we are wiping it out
-git fetch origin $DEV_BRANCH || (git checkout -b $DEV_BRANCH && git commit --allow-empty -m "sunnypilot v$VERSION release" && git push -u origin $DEV_BRANCH)
+git fetch --depth 1 origin $DEV_BRANCH || (git checkout -b $DEV_BRANCH && git commit --allow-empty -m "sunnypilot v$VERSION release" && git push -u origin $DEV_BRANCH)
 
 echo "[-] committing version $VERSION T=$SECONDS"
 git add -f .