mismatch mismatch

This reverts commit 01420fc08488374ec8fe3d17b757ccd1564d1328.

.github/CODEOWNERS

@@ -0,0 +1,11 @@
+*       @sunnypilot/dev-internal
+/.github/ @devtekve @sunnyhaibin
+/release/ci/ @devtekve @sunnyhaibin
+/tinygrad_repo @devtekve @Discountchubbs
+/tinygrad/ @devtekve @Discountchubbs
+/selfdrive/controls/lib/longitudinal_planner.py @devtekve @Discountchubbs
+/selfdrive/controls/lib/longitudinal_mpc_lib/long_mpc.py @devtekve @Discountchubbs
+/selfdrive/modeld/ @devtekve @Discountchubbs
+/sunnypilot/model* @devtekve @Discountchubbs
+/sunnypilot/sunnylink/ @devtekve
+/system/athena/ @devtekve

.github/workflows/build-all-tinygrad-models.yaml

@@ -78,7 +78,6 @@ jobs:
       - name: Get next recompiled dir number
         id: create-recompiled-dir
         env:
-          HF_TOKEN: ${{ secrets.HF_TOKEN }}
           HF_REPO: ${{ github.event.inputs.hf_repo }}
         run: |
           pip install huggingface_hub

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

@@ -341,7 +341,7 @@ jobs:
       - name: Upload model to HF
         if: ${{ inputs.target == 'small' || inputs.target == 'big' }}
         env:
-          HF_TOKEN: ${{ secrets.HF_TOKEN }}
+          HF_OIDC_RESOURCE: datasets/${{ env.HF_REPO }}
           ARTIFACT_NAME: ${{ steps.artifact.outputs.artifact_name }}
         run: |
           rm -f output/artifact_name.txt
@@ -367,7 +367,7 @@ jobs:
       - name: Generate DM metadata and upload to HF
         if: ${{ inputs.target == 'dm' }}
         env:
-          HF_TOKEN: ${{ secrets.HF_TOKEN }}
+          HF_OIDC_RESOURCE: datasets/${{ env.HF_REPO }}
         run: |
           export PYTHONPATH=$(pwd)
           python3 -c "
@@ -484,29 +484,11 @@ jobs:
           print(f'Chunked {pkl} into {len(targets)} chunks')
           "
 
-      - name: Compile DM warp
-        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"
-          MODEL_DIR="${{ github.workspace }}/openpilot/selfdrive/modeld"
-          DM_SIZE=$(python3 -c "from openpilot.common.transformations.model import DM_INPUT_SIZE as s; print(f'{s[0]}x{s[1]}')")
-
-          for res in $(python3 -c "from openpilot.common.transformations.camera import _ar_ox_fisheye as a, _os_fisheye as o; print(f'{a.width}x{a.height} {o.width}x{o.height}')"); do
-            WARP_PKL="${MODEL_DIR}/models/dm_warp_${res}_tinygrad.pkl"
-            taskset -c 7 env ${TG_FLAGS} python3 ${MODEL_DIR}/compile_dm_warp.py \
-              --camera-resolution ${res} \
-              --warp-to ${DM_SIZE} \
-              --output ${WARP_PKL}
-          done
-
       - 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/
-          cp ${{ github.workspace }}/openpilot/selfdrive/modeld/models/dm_warp_* dm_output/
 
       - name: Upload DM artifact
         uses: actions/upload-artifact@v4

.github/workflows/build-single-tinygrad-model.yaml

@@ -146,7 +146,7 @@ jobs:
 
       - name: Validate hf_repo and JSON version
         env:
-          HF_TOKEN: ${{ secrets.HF_TOKEN }}
+          HF_OIDC_RESOURCE: datasets/${{ inputs.hf_repo }}
         run: |
           if [ ! -f "$JSON_FILE" ]; then
             echo "JSON file $JSON_FILE does not exist!"
@@ -155,8 +155,13 @@ jobs:
           python3 -c "
           import sys
           from huggingface_hub import HfApi
-          HfApi().repo_info(repo_id=sys.argv[1], repo_type='dataset')
-          print(f'Success: Repo {sys.argv[1]} exists.')
+          try:
+              api = HfApi()
+              api.repo_info(repo_id=sys.argv[1], repo_type='dataset')
+              print(f'Success: Repo {sys.argv[1]} exists.')
+          except Exception as e:
+              print('HF validation failed:', e)
+              sys.exit(1)
           " "${{ inputs.hf_repo }}"
 
       - name: Download artifact name file
@@ -187,7 +192,7 @@ jobs:
 
       - name: Upload to Hugging Face
         env:
-          HF_TOKEN: ${{ secrets.HF_TOKEN }}
+          HF_OIDC_RESOURCE: datasets/${{ inputs.hf_repo }}
           ARTIFACT_NAME: ${{ steps.read-artifact-name.outputs.artifact_name }}
         run: |
           hf upload ${{ inputs.hf_repo }} \

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

@@ -46,13 +46,6 @@ runs:
             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}/${CANONICAL}.chunkmanifest"
-
-          if [ "$CANONICAL" = "dmonitoring_model_tinygrad.pkl" ]; then
-            for warp in dm_warp_1928x1208_tinygrad.pkl dm_warp_1344x760_tinygrad.pkl; do
-              ENCODED_URL=$(python3 -c "import urllib.parse; print(urllib.parse.quote('${BASE_URL}/${warp}', safe=':/'))")
-              printf '%s\t%s\n' "$ENCODED_URL" "${DEST_DIR}/${warp}" >> "$DOWNLOAD_LIST"
-            done
-          fi
         }
 
         echo "$MODELS_JSON" | jq -c '.[]' | while IFS= read -r model; do

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

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

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

@@ -216,9 +216,6 @@ jobs:
     needs: [ prepare_strategy ]
     runs-on: ubuntu-24.04
     if: ${{ needs.prepare_strategy.outputs.include_big_model == 'true' }}
-    concurrency:
-      group: prepare-chestnut
-      cancel-in-progress: false
     outputs:
       onnx_sha256: ${{ steps.resolve.outputs.onnx_sha256 }}
     env:
@@ -231,10 +228,8 @@ jobs:
         run: |
           REF="${{ github.head_ref || github.ref_name }}"
 
-          BLOB_SHA=$(gh api "repos/${GH_REPO}/contents/openpilot/selfdrive/modeld/models/big_driving_supercombo.onnx?ref=${REF}" --jq '.sha')
-          ONNX_HASH=$(gh api "repos/${GH_REPO}/git/blobs/${BLOB_SHA}" --jq '.content' | base64 -d | grep '^oid sha256:' | cut -d: -f2)
+          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: $ONNX_HASH"
-          [ -n "$ONNX_HASH" ] || { echo "::error::Failed to extract ONNX hash"; exit 1; }
           echo "onnx_sha256=$ONNX_HASH" >> $GITHUB_OUTPUT
 
           TINYGRAD_REF=$(gh api "repos/${GH_REPO}/contents/tinygrad_repo?ref=${REF}" --jq '.sha')
@@ -243,7 +238,7 @@ jobs:
           JSON_URL="https://huggingface.co/datasets/${HF_REPO}/resolve/main/${HF_DEFAULTS_PATH}/default_models.json"
 
           check_defaults() {
-            DEFAULTS=$(curl -fsSL "${JSON_URL}?t=$(date +%s)" 2>/dev/null) || return 1
+            DEFAULTS=$(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
             BUNDLE=$(echo "$DEFAULTS" | jq --arg hash "$ONNX_HASH" '.bundles[] | select(.onnx_sha256 == $hash)' 2>/dev/null)
@@ -257,35 +252,18 @@ jobs:
 
           echo "No matching model on HF — dispatching build"
           gh workflow run build-default-models.yaml --ref "$REF" -f target=big
-          sleep 10
 
-          BUILD_RUN_ID=$(gh run list --workflow build-default-models.yaml --branch "$REF" --limit 1 --json databaseId --jq '.[0].databaseId')
-          echo "Dispatched build run: $BUILD_RUN_ID"
-
-          echo "Waiting for build run to complete..."
+          echo "Polling HF for big model availability..."
           for i in $(seq 1 90); do
             sleep 30
-            STATUS=$(gh api "repos/${GH_REPO}/actions/runs/${BUILD_RUN_ID}" --jq '.status')
-            CONCLUSION=$(gh api "repos/${GH_REPO}/actions/runs/${BUILD_RUN_ID}" --jq '.conclusion')
-            echo "Poll $i/90: status=$STATUS conclusion=$CONCLUSION"
-            if [ "$STATUS" = "completed" ]; then
-              if [ "$CONCLUSION" = "success" ]; then
-                echo "Build run succeeded, verifying HF..."
-                sleep 10
-                if check_defaults; then
-                  echo "Big model verified on HF"
-                  exit 0
-                fi
-                echo "::error::Build succeeded but model not found on HF"
-                exit 1
-              else
-                echo "::error::Build run failed with conclusion=$CONCLUSION"
-                exit 1
-              fi
+            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::Build run did not complete within 45 minutes"
+          echo "::error::Big model not available on HF after 45 minutes"
           exit 1
         env:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
@@ -299,9 +277,6 @@ jobs:
   prepare_small_model:
     needs: [ prepare_strategy ]
     runs-on: ubuntu-24.04
-    concurrency:
-      group: prepare-small-model
-      cancel-in-progress: false
     outputs:
       driving_onnx_sha256: ${{ steps.resolve.outputs.driving_onnx_sha256 }}
     env:
@@ -314,10 +289,8 @@ jobs:
         run: |
           REF="${{ github.head_ref || github.ref_name }}"
 
-          BLOB_SHA=$(gh api "repos/${GH_REPO}/contents/openpilot/selfdrive/modeld/models/driving_supercombo.onnx?ref=${REF}" --jq '.sha')
-          DRIVING_HASH=$(gh api "repos/${GH_REPO}/git/blobs/${BLOB_SHA}" --jq '.content' | base64 -d | grep '^oid sha256:' | cut -d: -f2)
+          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: $DRIVING_HASH"
-          [ -n "$DRIVING_HASH" ] || { echo "::error::Failed to extract driving ONNX hash"; exit 1; }
           echo "driving_onnx_sha256=$DRIVING_HASH" >> $GITHUB_OUTPUT
 
           TINYGRAD_REF=$(gh api "repos/${GH_REPO}/contents/tinygrad_repo?ref=${REF}" --jq '.sha')
@@ -326,7 +299,7 @@ jobs:
           JSON_URL="https://huggingface.co/datasets/${HF_REPO}/resolve/main/${HF_DEFAULTS_PATH}/default_models.json"
 
           check_defaults() {
-            DEFAULTS=$(curl -fsSL "${JSON_URL}?t=$(date +%s)" 2>/dev/null) || return 1
+            DEFAULTS=$(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)
@@ -340,35 +313,18 @@ jobs:
 
           echo "No matching model on HF — dispatching build"
           gh workflow run build-default-models.yaml --ref "$REF" -f target=small
-          sleep 10
 
-          BUILD_RUN_ID=$(gh run list --workflow build-default-models.yaml --branch "$REF" --limit 1 --json databaseId --jq '.[0].databaseId')
-          echo "Dispatched build run: $BUILD_RUN_ID"
-
-          echo "Waiting for build run to complete..."
+          echo "Polling HF for model availability..."
           for i in $(seq 1 60); do
             sleep 30
-            STATUS=$(gh api "repos/${GH_REPO}/actions/runs/${BUILD_RUN_ID}" --jq '.status')
-            CONCLUSION=$(gh api "repos/${GH_REPO}/actions/runs/${BUILD_RUN_ID}" --jq '.conclusion')
-            echo "Poll $i/60: status=$STATUS conclusion=$CONCLUSION"
-            if [ "$STATUS" = "completed" ]; then
-              if [ "$CONCLUSION" = "success" ]; then
-                echo "Build run succeeded, verifying HF..."
-                sleep 10
-                if check_defaults; then
-                  echo "Small model verified on HF"
-                  exit 0
-                fi
-                echo "::error::Build succeeded but model not found on HF"
-                exit 1
-              else
-                echo "::error::Build run failed with conclusion=$CONCLUSION"
-                exit 1
-              fi
+            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 model build did not complete within 30 minutes"
+          echo "::error::Small driving model not available on HF after 30 minutes"
           exit 1
         env:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
@@ -382,9 +338,6 @@ jobs:
   prepare_dm_model:
     needs: [ prepare_strategy ]
     runs-on: ubuntu-24.04
-    concurrency:
-      group: prepare-dm-model
-      cancel-in-progress: false
     outputs:
       dm_onnx_sha256: ${{ steps.resolve.outputs.dm_onnx_sha256 }}
     env:
@@ -397,10 +350,8 @@ jobs:
         run: |
           REF="${{ github.head_ref || github.ref_name }}"
 
-          BLOB_SHA=$(gh api "repos/${GH_REPO}/contents/openpilot/selfdrive/modeld/models/dmonitoring_model.onnx?ref=${REF}" --jq '.sha')
-          DM_HASH=$(gh api "repos/${GH_REPO}/git/blobs/${BLOB_SHA}" --jq '.content' | base64 -d | grep '^oid sha256:' | cut -d: -f2)
+          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: $DM_HASH"
-          [ -n "$DM_HASH" ] || { echo "::error::Failed to extract DM ONNX hash"; exit 1; }
           echo "dm_onnx_sha256=$DM_HASH" >> $GITHUB_OUTPUT
 
           TINYGRAD_REF=$(gh api "repos/${GH_REPO}/contents/tinygrad_repo?ref=${REF}" --jq '.sha')
@@ -409,7 +360,7 @@ jobs:
           JSON_URL="https://huggingface.co/datasets/${HF_REPO}/resolve/main/${HF_DEFAULTS_PATH}/default_models.json"
 
           check_defaults() {
-            DEFAULTS=$(curl -fsSL "${JSON_URL}?t=$(date +%s)" 2>/dev/null) || return 1
+            DEFAULTS=$(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)
@@ -423,35 +374,18 @@ jobs:
 
           echo "No matching DM model on HF — dispatching build"
           gh workflow run build-default-models.yaml --ref "$REF" -f target=dm
-          sleep 10
 
-          BUILD_RUN_ID=$(gh run list --workflow build-default-models.yaml --branch "$REF" --limit 1 --json databaseId --jq '.[0].databaseId')
-          echo "Dispatched build run: $BUILD_RUN_ID"
-
-          echo "Waiting for build run to complete..."
+          echo "Polling HF for DM model availability..."
           for i in $(seq 1 60); do
             sleep 30
-            STATUS=$(gh api "repos/${GH_REPO}/actions/runs/${BUILD_RUN_ID}" --jq '.status')
-            CONCLUSION=$(gh api "repos/${GH_REPO}/actions/runs/${BUILD_RUN_ID}" --jq '.conclusion')
-            echo "Poll $i/60: status=$STATUS conclusion=$CONCLUSION"
-            if [ "$STATUS" = "completed" ]; then
-              if [ "$CONCLUSION" = "success" ]; then
-                echo "Build run succeeded, verifying HF..."
-                sleep 10
-                if check_defaults; then
-                  echo "DM model verified on HF"
-                  exit 0
-                fi
-                echo "::error::Build succeeded but DM model not found on HF"
-                exit 1
-              else
-                echo "::error::Build run failed with conclusion=$CONCLUSION"
-                exit 1
-              fi
+            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 build did not complete within 30 minutes"
+          echo "::error::DM model not available on HF after 30 minutes"
           exit 1
         env:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

openpilot/common/params_keys.h

@@ -139,6 +139,7 @@ inline static std::unordered_map<std::string, ParamKeyAttributes> keys = {
     {"ChestnutActive", {CLEAR_ON_MANAGER_START | CLEAR_ON_OFFROAD_TRANSITION | CLEAR_ON_IGNITION_ON, BOOL}},
     {"ChestnutLoading", {CLEAR_ON_MANAGER_START | CLEAR_ON_OFFROAD_TRANSITION | CLEAR_ON_IGNITION_ON, BOOL}},
     {"ChestnutModelError", {CLEAR_ON_MANAGER_START | CLEAR_ON_OFFROAD_TRANSITION | CLEAR_ON_IGNITION_ON, BOOL}},
+    {"AuxPowerSave", {PERSISTENT | BACKUP, BOOL}},
     {"Version", {PERSISTENT, STRING}},
 
     // --- sunnypilot params --- //

openpilot/selfdrive/ui/ui_state.py

@@ -225,6 +225,7 @@ class UIState(UIStateSP):
                              ChestnutState.UNCOMPILED if detected else ChestnutState.DISCONNECTED)
       return
 
+    self.chestnut_present = self.chestnut_present or detected
     model_seen = self.sm.recv_frame["modelV2"] > self.started_frame
     if not self.chestnut_present:
       self.chestnut_state = ChestnutState.DISCONNECTED

openpilot/sunnypilot/modeld_v2/compile_modeld.py

@@ -32,7 +32,7 @@ def _patch_tinygrad_fetch_fw():
   helpers.fetch_fw = fetch_fw
 _patch_tinygrad_fetch_fw()
 
-import openpilot.selfdrive.modeld.compile_modeld as stock
+from openpilot.selfdrive.modeld.compile_modeld import NV12Frame, make_frame_prepare, sample_desire, sample_skip, shift_and_sample
 from tinygrad import dtypes
 from tinygrad.device import Device
 from tinygrad.engine.jit import TinyJit
@@ -41,7 +41,8 @@ from tinygrad.tensor import Tensor
 MODEL_TYPES = ('vision_policy', 'supercombo', 'vision_multi_policy')
 WARP_INPUTS = ['tfm', 'big_tfm']
 POLICY_INPUTS = ['img_q', 'big_img_q', 'feat_q', 'desire_q', 'packed_npy_inputs']
-nv12_copy_size = stock.nv12_copy_size
+WARP_DEV = os.getenv('WARP_DEV')
+
 
 def _detect_desire_key(shapes: dict) -> str | None:
   return next((key for key in shapes if key.startswith('desire')), None)
@@ -138,9 +139,7 @@ def make_supercombo_input_queues(input_shapes: dict, frame_skip: int,
   return generate_queues_and_npy(input_shapes, frame_skip, device, is_supercombo=True)
 
 
-def make_random_images(keys, shape, device, rng):
-  if device == 'NPY':
-    return {k: Tensor(rng.integers(0, 256, size=shape, dtype=np.uint8), device='NPY').realize() for k in keys}
+def make_random_images(keys, shape, device):
   return {k: Tensor.randint(shape, low=0, high=256, dtype=dtypes.uint8, device=device).realize() for k in keys}
 
 
@@ -153,16 +152,14 @@ def make_warp_queues(device=Device.DEFAULT):
   return queues, npy
 
 
-def make_warp(nv12: stock.NV12Frame, model_w: int, model_h: int):
-  frame_prepare = stock.make_frame_prepare(nv12, model_w, model_h)
+def make_warp(nv12: NV12Frame, model_w: int, model_h: int):
+  frame_prepare = make_frame_prepare(nv12, model_w, model_h)
+  WARP_DEV = os.getenv('WARP_DEV', Device.DEFAULT)
 
   def warp(tfm, big_tfm, frame, big_frame):
-    tfm = tfm.to(Device.DEFAULT)
-    big_tfm = big_tfm.to(Device.DEFAULT)
-    if Device.DEFAULT == 'AMD':
-      frame = frame.to(Device.DEFAULT)
-      big_frame = big_frame.to(Device.DEFAULT)
-    Tensor.realize(tfm, big_tfm, frame, big_frame)
+    tfm = tfm.to(WARP_DEV)
+    big_tfm = big_tfm.to(WARP_DEV)
+    Tensor.realize(tfm, big_tfm)
 
     warped_frame = frame_prepare(frame, tfm).unsqueeze(0)
     warped_big_frame = frame_prepare(big_frame, big_tfm).unsqueeze(0)
@@ -171,8 +168,8 @@ def make_warp(nv12: stock.NV12Frame, model_w: int, model_h: int):
 
 
 def make_run_policy(vision_runner, policy_runners: list, features_slice: slice, frame_skip: int, input_shapes: dict):
-  sample_skip_fn = partial(stock.sample_skip, frame_skip=frame_skip)
-  sample_desire_fn = partial(stock.sample_desire, frame_skip=frame_skip)
+  sample_skip_fn = partial(sample_skip, frame_skip=frame_skip)
+  sample_desire_fn = partial(sample_desire, frame_skip=frame_skip)
 
   desire_key = _detect_desire_key(input_shapes)
   road_key, wide_key = _detect_vision_keys(input_shapes)
@@ -189,14 +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 = stock.shift_and_sample(img_q, warped_dev[0:1], sample_skip_fn)
-    big_img = stock.shift_and_sample(big_img_q, warped_dev[1:2], sample_skip_fn)
+    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 = stock.shift_and_sample(desire_q, desire_dev.reshape(1, 1, -1), sample_desire_fn)
+    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():
@@ -205,13 +202,13 @@ 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'] = stock.shift_and_sample(feat_q, prev_feat_dev.reshape(1, 1, -1), sample_skip_fn).reshape(input_shapes['features_buffer'])
+      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()
       if 'features_buffer' not in inputs:
         new_feat = vision_out_cast[:, features_slice].reshape(1, -1).unsqueeze(0)
-        inputs['features_buffer'] = stock.shift_and_sample(feat_q, new_feat, sample_skip_fn).realize()
+        inputs['features_buffer'] = shift_and_sample(feat_q, new_feat, sample_skip_fn).realize()
       policy_outs = [next(iter(pol_runner(inputs).values())).cast('float32').realize() for pol_runner in policy_runners]
       return (vision_out_cast, *policy_outs) if len(policy_outs) > 1 else (vision_out_cast, policy_outs[0])
 
@@ -222,28 +219,27 @@ def make_run_policy(vision_runner, policy_runners: list, features_slice: slice,
     policy_out = next(iter(policy_runners[0](inputs).values())).cast('float32').realize()
     if 'features_buffer' not in inputs and features_slice is not None:
       new_feat = policy_out[:, features_slice].reshape(1, -1).unsqueeze(0)
-      stock.shift_and_sample(feat_q, new_feat, sample_skip_fn).realize()
+      shift_and_sample(feat_q, new_feat, sample_skip_fn).realize()
     return policy_out
 
   return run_policy
 
 
-def compile_jit(jit, input_keys, make_queues, make_random_inputs=None, benchmark_runs: int = 1):
+def compile_jit(jit, make_random_inputs, input_keys, make_queues):
   SEED = 42
-  def random_inputs_run(fn, seed, n_runs, test_val=None, test_buffers=None, expect_match=True):
-    queues_res = make_queues(Device.DEFAULT)
-    input_queues, npy = queues_res[0], queues_res[1]
-    frame_views = queues_res[2] if len(queues_res) > 2 else {}
+  def random_inputs_run(fn, seed, test_val=None, test_buffers=None, expect_match=True):
+    input_queues, npy = make_queues(Device.DEFAULT)
     rng = np.random.default_rng(seed)
     Tensor.manual_seed(seed)
 
+    testing = test_val is not None or test_buffers is not None
+    n_runs = 1 if testing else 3
+
     for i in range(n_runs):
       for v in npy.values():
         v[:] = rng.standard_normal(v.shape).astype(v.dtype)
-      for v in frame_views.values():
-        v[:] = rng.integers(0, 256, size=v.shape, dtype=np.uint8)
       Device.default.synchronize()
-      random_inputs = make_random_inputs(rng=rng) if make_random_inputs is not None else {}
+      random_inputs = make_random_inputs()
       st = time.perf_counter()
       outs = fn(**{k: input_queues[k] for k in input_keys if k in input_queues}, **random_inputs)
       mt = time.perf_counter()
@@ -264,15 +260,14 @@ def compile_jit(jit, input_keys, make_queues, make_random_inputs=None, benchmark
     return val, buffers
 
   print('capture + replay')
-  test_val, test_buffers = random_inputs_run(jit, SEED, 3)
-  print(f'pickle round trip ({benchmark_runs} runs per seed)')
+  test_val, test_buffers = random_inputs_run(jit, SEED)
+  print('pickle round trip')
   with tempfile.TemporaryFile(dir=".") as f:
     dump_oob(jit, f)
     f.seek(0)
-    loaded_jit = load_oob(f)
-  random_inputs_run(loaded_jit, SEED, benchmark_runs, test_val, test_buffers, expect_match=True)
-  random_inputs_run(loaded_jit, SEED+1, benchmark_runs, test_val, test_buffers, expect_match=False)
-  return jit
+    deserialized_jit = load_oob(f)
+  random_inputs_run(deserialized_jit, SEED, test_val=test_val, test_buffers=test_buffers)
+  return deserialized_jit
 
 
 def _parse_size(size_str: str) -> tuple[int, int]:
@@ -322,7 +317,6 @@ if __name__ == "__main__":
   parser.add_argument('--model-size', type=_parse_size, required=True, help='model input WxH')
   parser.add_argument('--camera-resolutions', type=_parse_size, nargs='+', required=True)
   parser.add_argument('--frame-skip', type=int, default=None, help='frame skip value (auto-derived if not provided)')
-  parser.add_argument('--benchmark-runs', type=int, default=1, help='benchmark runs')
   parser.add_argument('--output', required=True)
 
   parser.add_argument('--vision-onnx', help='vision ONNX (for split models)')
@@ -341,65 +335,48 @@ if __name__ == "__main__":
   args.on_policy_onnx = read_file_chunked_to_disk(args.on_policy_onnx)
   args.supercombo_onnx = read_file_chunked_to_disk(args.supercombo_onnx)
 
-  if args.model_type == 'supercombo':
+  vision_runner = OnnxRunner(args.vision_onnx) if args.vision_onnx else None
+
+  if args.model_type == 'vision_policy':
+    assert vision_runner and args.policy_onnx
+    policy_runners = [OnnxRunner(args.policy_onnx)]
+    output_data['metadata'] = {'vision': make_metadata_dict(args.vision_onnx), 'policy': make_metadata_dict(args.policy_onnx)}
+  elif args.model_type == 'supercombo':
     assert args.supercombo_onnx
-    model_metadata = make_metadata_dict(args.supercombo_onnx)
-    output_data['metadata'] = {'model': model_metadata, **model_metadata}
-    output_data['input_devices'] = {'model': Device.DEFAULT}
-    output_data['run_model'] = {}
-    derived_frame_skip = args.frame_skip or derive_frame_skip({}, model_metadata['input_shapes'])
-    model_runner = OnnxRunner(args.supercombo_onnx)
-    run_policy = stock.make_run_policy(model_runner, model_metadata, derived_frame_skip)
-    for cam_w, cam_h in args.camera_resolutions:
-      print(f"Compiling unified run_model JIT for {cam_w}x{cam_h}...")
-      nv12 = stock.NV12Frame(cam_w, cam_h, *get_nv12_info(cam_w, cam_h))
-      frame_copy_size = stock.nv12_copy_size(nv12.stride, nv12.y_height, nv12.uv_height)
-      make_model_queues = partial(stock.make_input_queues, model_metadata['input_shapes'], derived_frame_skip,
-                                  frame_copy_size=frame_copy_size)
-      warp = stock.make_warp(nv12, model_w, model_h)
-      run_model_jit = TinyJit(stock.make_run_model(warp, run_policy, model_metadata, frame_copy_size), prune=True)
-      output_data['run_model'][(cam_w, cam_h)] = compile_jit(run_model_jit, stock.MODELD_INPUTS, make_model_queues, benchmark_runs=args.benchmark_runs)
-  else:
-    vision_runner = OnnxRunner(args.vision_onnx) if args.vision_onnx else None
-    if args.model_type == 'vision_policy':
-      assert vision_runner and args.policy_onnx
-      policy_runners = [OnnxRunner(args.policy_onnx)]
-      output_data['metadata'] = {'vision': make_metadata_dict(args.vision_onnx), 'policy': make_metadata_dict(args.policy_onnx)}
-    elif args.model_type == 'vision_multi_policy':
-      assert vision_runner
-      policy_runners, policy_names = _load_policy_runners(args)
-      output_data['metadata'] = {'vision': make_metadata_dict(args.vision_onnx)}
-      for name in policy_names:
-        runner_arg = getattr(args, f"{name}_onnx")
-        output_data['metadata'][name] = make_metadata_dict(runner_arg)
+    policy_runners = [OnnxRunner(args.supercombo_onnx)]
+    output_data['metadata'] = {'model': make_metadata_dict(args.supercombo_onnx)}
+  elif args.model_type == 'vision_multi_policy':
+    assert vision_runner
+    policy_runners, policy_names = _load_policy_runners(args)
+    output_data['metadata'] = {'vision': make_metadata_dict(args.vision_onnx)}
+    for name in policy_names:
+      runner_arg = getattr(args, f"{name}_onnx")
+      output_data['metadata'][name] = make_metadata_dict(runner_arg)
 
-    policy_keys = [key for key in output_data['metadata'].keys() if key != 'vision']
-    first_policy_meta = output_data['metadata'][policy_keys[0]] if policy_keys else {}
-    vision_meta = output_data['metadata'].get('vision', {})
+  policy_keys = [key for key in output_data['metadata'].keys() if key != 'vision']
+  first_policy_meta = output_data['metadata'][policy_keys[0]] if policy_keys else {}
+  vision_meta = output_data['metadata'].get('vision', {})
 
-    derived_frame_skip = args.frame_skip or derive_frame_skip(vision_meta.get('input_shapes', {}), first_policy_meta.get('input_shapes', {}))
-    all_shapes = {key: value for meta in output_data['metadata'].values() for key, value in meta['input_shapes'].items()}
-    feat_meta = output_data['metadata'].get('vision') or output_data['metadata'].get('policy')
-    assert feat_meta is not None
-    features_slice = feat_meta['output_slices']['hidden_state']
+  derived_frame_skip = args.frame_skip or derive_frame_skip(vision_meta.get('input_shapes', {}), first_policy_meta.get('input_shapes', {}))
+  all_shapes = {key: value for meta in output_data['metadata'].values() for key, value in meta['input_shapes'].items()}
+  feat_meta = output_data['metadata'].get('vision') or output_data['metadata'].get('model') or output_data['metadata'].get('policy')
+  assert feat_meta is not None
+  features_slice = feat_meta['output_slices']['hidden_state']
+  is_supercombo = vision_runner is None
 
-    print(f"Compiling run_policy JIT (model_size={model_w}x{model_h}, frame_skip={derived_frame_skip})...")
-    run_policy_func = make_run_policy(vision_runner, policy_runners, features_slice, derived_frame_skip, all_shapes)
-    run_policy_jit = TinyJit(run_policy_func, prune=True)
-    make_policy_queues = partial(generate_queues_and_npy, all_shapes, derived_frame_skip, is_supercombo=False)
-    make_random_model_inputs = partial(make_random_images, keys=['warped'], shape=(2, 6, model_h // 2, model_w // 2), device=Device.DEFAULT)
-    output_data['run_policy'] = compile_jit(run_policy_jit, POLICY_INPUTS, make_policy_queues, make_random_inputs=make_random_model_inputs)
+  print(f"Compiling run_policy JIT (model_size={model_w}x{model_h}, frame_skip={derived_frame_skip})...")
+  run_policy_func = make_run_policy(vision_runner, policy_runners, features_slice, derived_frame_skip, all_shapes)
+  run_policy_jit = TinyJit(run_policy_func, prune=True)
+  make_policy_queues = partial(generate_queues_and_npy, all_shapes, derived_frame_skip, is_supercombo=is_supercombo)
+  make_random_model_inputs = partial(make_random_images, keys=['warped'], shape=(2, 6, model_h // 2, model_w // 2), device=WARP_DEV)
+  output_data['run_policy'] = compile_jit(run_policy_jit, make_random_model_inputs, POLICY_INPUTS, make_policy_queues)
 
-    for cam_w, cam_h in args.camera_resolutions:
-      print(f"Compiling warp JIT for {cam_w}x{cam_h}...")
-      nv12 = stock.NV12Frame(cam_w, cam_h, *get_nv12_info(cam_w, cam_h))
-      frame_copy_size = stock.nv12_copy_size(nv12.stride, nv12.y_height, nv12.uv_height)
-      warp_input_dev = 'NPY' if Device.DEFAULT == 'AMD' else Device.DEFAULT
-      make_random_warp_inputs = partial(make_random_images, keys=['frame', 'big_frame'], shape=frame_copy_size, device=warp_input_dev)
-      warp = TinyJit(make_warp(nv12, model_w, model_h), prune=True)
-      output_data[(cam_w, cam_h)] = compile_jit(warp, WARP_INPUTS, make_warp_queues, make_random_inputs=make_random_warp_inputs)
-
-    output_data['metadata']['warp_dev'] = Device.DEFAULT
+  for cam_w, cam_h in args.camera_resolutions:
+    print(f"Compiling warp JIT for {cam_w}x{cam_h}...")
+    nv12 = NV12Frame(cam_w, cam_h, *get_nv12_info(cam_w, cam_h))
+    make_random_warp_inputs = partial(make_random_images, keys=['frame', 'big_frame'], shape=nv12.size, device=WARP_DEV)
+    warp = TinyJit(make_warp(nv12, model_w, model_h), prune=True)
+    output_data[(cam_w, cam_h)] = compile_jit(warp, make_random_warp_inputs, WARP_INPUTS, make_warp_queues)
 
   with open(args.output, "wb") as file:
     dump_oob(output_data, file)

openpilot/sunnypilot/modeld_v2/constants.py

@@ -14,8 +14,6 @@ class ModelConstants:
 
   # model inputs constants
   MODEL_FREQ = 20
-  MODEL_RUN_FREQ = 20
-  MODEL_CONTEXT_FREQ = 5
   FEATURE_LEN = 512
   FULL_HISTORY_BUFFER_LEN = 99
   DESIRE_LEN = 8

openpilot/sunnypilot/modeld_v2/modeld.py

@@ -6,7 +6,6 @@ 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.
 """
 
-from collections.abc import Callable
 import os
 os.environ['GMMU'] = '0'
 import numpy as np
@@ -38,18 +37,11 @@ from openpilot.selfdrive.controls.lib.desire_helper import DesireHelper
 from openpilot.selfdrive.controls.lib.drive_helpers import get_accel_from_plan, smooth_value
 from openpilot.selfdrive.modeld.modeld import ChestnutState
 
-from openpilot.selfdrive.modeld.compile_modeld import (
-  MODELD_INPUTS,
-  make_input_queues as make_stock_input_queues,
-)
 from openpilot.sunnypilot.modeld_v2.fill_model_msg import fill_model_msg, fill_pose_msg, PublishState, get_curvature_from_output
-from openpilot.sunnypilot.modeld_v2.parse_model_outputs import Parser as CombinedParser
-from openpilot.sunnypilot.modeld_v2.constants import ModelConstants, Plan
+from openpilot.sunnypilot.modeld_v2.constants import Plan
 from openpilot.sunnypilot.modeld_v2.meta_helper import load_meta_constants
 from openpilot.sunnypilot.modeld_v2.camera_offset_helper import CameraOffsetHelper
-from openpilot.sunnypilot.modeld_v2.compile_modeld import (derive_frame_skip, make_split_input_queues,
-                                                           make_supercombo_input_queues, nv12_copy_size,
-                                                           WARP_INPUTS, POLICY_INPUTS)
+from openpilot.sunnypilot.modeld_v2.compile_modeld import derive_frame_skip, make_split_input_queues, make_supercombo_input_queues, WARP_INPUTS, POLICY_INPUTS
 from openpilot.sunnypilot.livedelay.helpers import get_lat_delay
 from openpilot.sunnypilot.modeld_v2.modeld_base import ModelStateBase
 from openpilot.sunnypilot.models.helpers import get_active_bundle
@@ -118,41 +110,36 @@ class ModelState(ModelStateBase):
     cloudlog.warning(f"loading combined pkl: {pkl_path}")
     jits = load_oob(open_file_chunked(pkl_path))
 
-    metadata = jits['metadata']
-    self.use_frame_buffers = metadata.get('warp_dev') == 'AMD'
-    self.WARP_DEV = metadata.get('warp_dev', 'QCOM') if COMMA_HARDWARE else 'CPU'
-    self.DEV = ('AMD' if self.chestnut else 'QCOM') if COMMA_HARDWARE else 'CPU'
+    self.WARP_DEV = 'QCOM' if COMMA_HARDWARE else 'CPU'
+    self.DEV = 'AMD' if self.chestnut else self.WARP_DEV
     self.QUEUE_DEV = self.DEV
-    self.is_run_model = 'run_model' in jits
+    metadata = jits['metadata']
 
-    nv12_info = get_nv12_info(cam_w, cam_h)
-    self.frame_copy_size = nv12_copy_size(*nv12_info[:3])
-    self.full_frames: dict = {}
-    self._blob_cache: dict = {}
-    self.frame_buffers: dict = {}
+    self.is_legacy_model = 'run_policy' not in jits  # remove after next recompile
+    if self.is_legacy_model:
+      self.warp = jits[(cam_w, cam_h)]['warp_enqueue']
+      self.run_policy = jits[(cam_w, cam_h)]['run_policy']
+    else:
+      self.run_policy = jits['run_policy']
+      self.warp = jits[(cam_w, cam_h)]
 
-    if self.is_run_model or 'model' in metadata:
-      model_metadata = metadata.get('model', metadata)
-      self.input_shapes = model_metadata['input_shapes']
+    if 'model' in metadata:
+      model_metadata = metadata['model']
       self.vision_output_slices = model_metadata['output_slices']
       self.policy_output_slices = {}
       self._policy_slices_list = []
       self._combined_model_type = 'supercombo'
-      self._vision_input_names = [key for key in self.input_shapes if 'img' in key]
-      self.frame_skip = derive_frame_skip({}, self.input_shapes)
-      if self.is_run_model:
-        self.input_queues, self.numpy_inputs, self.frame_buffers = make_stock_input_queues(
-          self.input_shapes, self.frame_skip, device=self.DEV, frame_copy_size=self.frame_copy_size)
-        self.frame_views, self.npy = self.frame_buffers, self.numpy_inputs
-        self.run_model, self.run_policy, self.warp = jits['run_model'][(cam_w, cam_h)], None, None
-      else:
-        self.input_queues, self.numpy_inputs = make_supercombo_input_queues(self.input_shapes, self.frame_skip, device=self.QUEUE_DEV)
-        self.run_model, self.run_policy, self.warp = None, jits['run_policy'], jits[(cam_w, cam_h)]
+      self._vision_input_names = [key for key in model_metadata['input_shapes'] if 'img' in key]
+      frame_skip = derive_frame_skip({}, model_metadata['input_shapes'])
+      self.input_queues, self.numpy_inputs = make_supercombo_input_queues(model_metadata['input_shapes'],
+                                                                          frame_skip, device=self.QUEUE_DEV)
     else:
-      self.run_model, self.run_policy, self.warp = None, jits['run_policy'], jits[(cam_w, cam_h)]
       vision_metadata = metadata['vision']
-      policy_keys = [k for k in metadata if k not in ('vision', 'warp_dev')]
-      self._combined_model_type = 'split' if policy_keys == ['policy'] else 'multi_policy'
+      policy_keys = [k for k in metadata if k != 'vision']
+      if policy_keys == ['policy']:
+        self._combined_model_type = 'split'
+      else:
+        self._combined_model_type = 'multi_policy'
       self.vision_output_slices = vision_metadata['output_slices']
       self._policy_keys = policy_keys
       self._policy_slices_list = [metadata[k]['output_slices'] for k in policy_keys]
@@ -168,49 +155,54 @@ class ModelState(ModelStateBase):
     self._desire_key = next(key for key in self.numpy_inputs if key.startswith('desire'))
     self._road_key = next(key for key in self._vision_input_names if 'big' not in key)
     self._wide_key = next(key for key in self._vision_input_names if 'big' in key)
-    self.frame_buf_params = dict.fromkeys(self._vision_input_names, nv12_info)
 
     is_20hz = bundle.is20hz if bundle else self._combined_model_type in ('split', 'multi_policy')
     if is_20hz:
       from openpilot.sunnypilot.models.split_model_constants import SplitModelConstants
       self.constants = SplitModelConstants()
     else:
+      from openpilot.sunnypilot.modeld_v2.constants import ModelConstants
       self.constants = ModelConstants()
 
     if self._combined_model_type != 'supercombo':
       from openpilot.sunnypilot.modeld_v2.parse_model_outputs_split import Parser as SplitParser
       self.parser = SplitParser()
     else:
+      from openpilot.sunnypilot.modeld_v2.parse_model_outputs import Parser as CombinedParser
       self.parser = CombinedParser()
 
     self.prev_desire = np.zeros(self.constants.DESIRE_LEN, dtype=np.float32)
+    self.full_frames: dict = {}
+    self._blob_cache: dict = {}
+    nv12_info = get_nv12_info(cam_w, cam_h)
+    self.frame_buf_params = dict.fromkeys(self._vision_input_names, nv12_info)
 
-    if not self.is_run_model:
-      if self.use_frame_buffers:
-        self.frame_buffers = {k: np.zeros(self.frame_copy_size, dtype=np.uint8) for k in self._vision_input_names}
-        self.full_frames = {k: Tensor(self.frame_buffers[k], device='NPY').realize() for k in self._vision_input_names}
-      else:
-        self.full_frames = {k: Tensor(np.zeros(nv12_info[3], dtype=np.uint8), device=self.WARP_DEV).contiguous().realize() for k in self._vision_input_names}
-      self.warp(**{k: self.input_queues[k] for k in WARP_INPUTS}, frame=self.full_frames[self._road_key], big_frame=self.full_frames[self._wide_key])
+    yuv_size = self.frame_buf_params[self._road_key][3]
+    frame_tensor = Tensor(np.zeros(yuv_size, dtype=np.uint8), device=self.WARP_DEV).contiguous().realize()
+    big_frame_tensor = Tensor(np.zeros(yuv_size, dtype=np.uint8), device=self.WARP_DEV).contiguous().realize()
+
+    if self.is_legacy_model: # Remove this conditional hack after recompile
+      self.warp(**self.input_queues, frame=frame_tensor, big_frame=big_frame_tensor)
+    else:
+      self.warp(**{k: self.input_queues[k] for k in WARP_INPUTS}, frame=frame_tensor, big_frame=big_frame_tensor)
 
   def warmup(self) -> None:
-    dummy_size = self.frame_copy_size if (self.is_run_model or self.use_frame_buffers) else self.frame_buf_params[self._road_key][3]
-    dummy_frames = {k: np.zeros(dummy_size, dtype=np.uint8) for k in self._vision_input_names}
+    dummy_frames = {k: np.zeros(self.frame_buf_params[k][3], dtype=np.uint8) for k in self._vision_input_names}
     transforms = {k: np.eye(3, dtype=np.float32) for k in [self._road_key, self._wide_key] if k}
-    dummy_inputs = {k: np.zeros(v.shape, dtype=v.dtype) for k, v in self.numpy_inputs.items() if k not in ['tfm', 'big_tfm', 'prev_feat']}
-    self.run(dummy_frames, transforms, dummy_inputs)
-    if self.is_run_model:
-      self.input_queues, self.numpy_inputs, self.frame_buffers = make_stock_input_queues(
-        self.input_shapes, self.frame_skip, device=self.DEV, frame_copy_size=self.frame_copy_size)
-      self.frame_views = self.frame_buffers
-      self.npy = self.numpy_inputs
-    else:
-      for v in self.numpy_inputs.values():
-        v[:] = 0
-      if not self.use_frame_buffers:
-        self.full_frames.clear()
-        self._blob_cache.clear()
+
+    dummy_inputs = {}
+    for k, v in self.numpy_inputs.items():
+      if k not in ['tfm', 'big_tfm', 'prev_feat']:
+        dummy_inputs[k] = np.zeros(v.shape, dtype=v.dtype)
+
+    self.run(dummy_frames, transforms, dummy_inputs, prepare_only=False)
+
+    for v in self.numpy_inputs.values():
+      v[:] = 0
     self.prev_desire[:] = 0
+    self.full_frames.clear()
+    self._blob_cache.clear()
+
 
   @property
   def mlsim(self) -> bool:
@@ -225,49 +217,45 @@ class ModelState(ModelStateBase):
     return self._desire_key
 
   def run(self, bufs: dict[str, VisionBuf], transforms: dict[str, np.ndarray],
-          inputs: dict[str, np.ndarray],
-          after_enqueue: Callable[[], None] | None = None) -> dict[str, np.ndarray] | None:
-    if self.is_run_model or self.use_frame_buffers:
-      for key, buf in bufs.items():
-        data = buf.data if hasattr(buf, 'data') else buf
-        np.copyto(self.frame_buffers[key], np.frombuffer(data, dtype=np.uint8, count=self.frame_copy_size))
-    else:
-      for key, buf in bufs.items():
-        ptr = np.frombuffer(buf.data, dtype=np.uint8).ctypes.data
-        cache_key = (key, ptr)
-        if cache_key not in self._blob_cache:
-          self._blob_cache[cache_key] = Tensor.from_blob(ptr, (self.frame_buf_params[key][3],), dtype='uint8', device=self.WARP_DEV)
-        self.full_frames[key] = self._blob_cache[cache_key]
+                inputs: dict[str, np.ndarray], prepare_only: bool) -> dict[str, np.ndarray] | None:
+    for key in bufs.keys():
+      ptr = np.frombuffer(bufs[key].data, dtype=np.uint8).ctypes.data
+      yuv_size = self.frame_buf_params[key][3]
+      cache_key = (key, ptr)
+      if cache_key not in self._blob_cache:
+        self._blob_cache[cache_key] = Tensor.from_blob(ptr, (yuv_size,), dtype='uint8', device=self.WARP_DEV)
+      self.full_frames[key] = self._blob_cache[cache_key]
 
     desire_key = self.desire_key
     inputs[desire_key][0] = 0
     self.numpy_inputs[desire_key][:] = np.where(inputs[desire_key] - self.prev_desire > .99, inputs[desire_key], 0)
     self.prev_desire[:] = inputs[desire_key]
-
     for key in ('traffic_convention', 'lateral_control_params', 'action_t'):
       if key in self.numpy_inputs and key in inputs:
         self.numpy_inputs[key][:] = inputs[key]
 
-    self.numpy_inputs['tfm'][:, :] = transforms[self._road_key].reshape(3, 3)
-    self.numpy_inputs['big_tfm'][:, :] = transforms[self._wide_key].reshape(3, 3)
+    road_key = self._road_key
+    wide_key = self._wide_key
+    self.numpy_inputs['tfm'][:, :] = transforms[road_key].reshape(3, 3)
+    self.numpy_inputs['big_tfm'][:, :] = transforms[wide_key].reshape(3, 3)
 
-    if self.is_run_model:
-      outs, = self.run_model(**{k: self.input_queues[k] for k in MODELD_INPUTS})
-      raw_outputs = outs
+    if self.is_legacy_model:  # remove after next recompile
+      if prepare_only:
+        self.warp(**self.input_queues, frame=self.full_frames[road_key], big_frame=self.full_frames[wide_key])
+        return None
+      raw_outputs = self.run_policy(**self.input_queues, frame=self.full_frames[road_key], big_frame=self.full_frames[wide_key])
     else:
-      warped = self.warp(**{k: self.input_queues[k] for k in WARP_INPUTS}, frame=self.full_frames[self._road_key], big_frame=self.full_frames[self._wide_key])
+      if prepare_only:
+        self.warp(**{k: self.input_queues[k] for k in WARP_INPUTS}, frame=self.full_frames[road_key], big_frame=self.full_frames[wide_key])
+        return None
+      warped = self.warp(**{k: self.input_queues[k] for k in WARP_INPUTS}, frame=self.full_frames[road_key], big_frame=self.full_frames[wide_key])
       raw_outputs = self.run_policy(**{k: self.input_queues[k] for k in POLICY_INPUTS if k in self.input_queues}, warped=warped)
 
-    if after_enqueue is not None:
-      after_enqueue()
-
     if self._combined_model_type == 'supercombo':
       model_output = raw_outputs.numpy().flatten()
-      if self.chestnut and not np.all(np.isfinite(model_output)):
-        raise RuntimeError("model output not finite")
       sliced = {k: model_output[np.newaxis, v] for k, v in self.vision_output_slices.items()}
       outputs = self.parser.parse_outputs(sliced)
-      if 'prev_feat' in self.numpy_inputs and 'hidden_state' in self.vision_output_slices:
+      if 'prev_feat' in self.numpy_inputs:
         self.numpy_inputs['prev_feat'][:] = model_output[self.vision_output_slices['hidden_state']]
     else:
       vision_output = raw_outputs[0].numpy().flatten()
@@ -297,6 +285,9 @@ class ModelState(ModelStateBase):
       buf[0, :-1] = buf[0, 1:]
       buf[0, -1, :] = outputs['desired_curvature'][0, :] if not self.mlsim else 0
 
+    if self.chestnut and not np.all(np.isfinite(outputs.get('plan', np.array([0.])))):
+      raise RuntimeError("model output not finite")
+
     return outputs
 
   def get_action_from_model(self, model_output: dict[str, np.ndarray], prev_action: log.ModelDataV2.Action,
@@ -382,11 +373,7 @@ def main(demo=False):
     loader.start()
     loader.join(BIG_MODEL_TIMEOUT)
     model = big_model
-    if model is None:
-      params.put_bool("ChestnutModelError", True)
     params.put_bool("ChestnutActive", model is not None)
-    if model is not None:
-      params.remove("ChestnutModelError")
 
   small_model = ModelState(cam_w=vipc_client_main.width, cam_h=vipc_client_main.height, chestnut=False) if model is None or CHESTNUT else None
   if model is None:
@@ -500,6 +487,9 @@ def main(demo=False):
     run_count = run_count + 1
 
     frame_drop_ratio = frames_dropped / (1 + frames_dropped)
+    prepare_only = vipc_dropped_frames > 0
+    if prepare_only:
+      cloudlog.error(f"skipping model eval. Dropped {vipc_dropped_frames} frames")
 
     bufs = {name: buf_extra if 'big' in name else buf_main for name in model.vision_input_names}
     transforms = {name: model_transform_extra if 'big' in name else model_transform_main for name in model.vision_input_names}
@@ -522,14 +512,11 @@ def main(demo=False):
 
     mt1 = time.perf_counter()
     try:
-      send_chestnut = (chestnut_state is not None and
-                       run_count % round(model.constants.MODEL_FREQ / SERVICE_LIST['chestnutState'].frequency) == 0)
-      model_output = model.run(bufs, transforms, inputs, chestnut_state.send if send_chestnut else None)
+      model_output = model.run(bufs, transforms, inputs, prepare_only)
     except Exception:
       if not params.get_bool("ChestnutActive"):
         raise
       cloudlog.exception("chestnut failed, falling back to small")
-      params.put_bool("ChestnutModelError", True)
       params.put_bool("ChestnutActive", False)
       assert small_model is not None
       model = small_model
@@ -572,6 +559,9 @@ def main(demo=False):
       pm.send('modelDataV2SP', mdv2sp_send)
     last_vipc_frame_id = meta_main.frame_id
 
+    if chestnut_state is not None and run_count % round(model.constants.MODEL_FREQ / SERVICE_LIST['chestnutState'].frequency) == 0:
+      chestnut_state.send()
+
 if __name__ == "__main__":
   try:
     import argparse

openpilot/sunnypilot/modeld_v2/tests/test_combined_pkl_loader.py

@@ -103,23 +103,6 @@ class TestStockEquivalence(OpenpilotTestCase):
     assert state.vision_output_slices == arch.metadata_structure['vision']['output_slices']
     assert state.policy_output_slices == arch.metadata_structure['policy']['output_slices']
 
-  def test_unified_run_model(self, tmp_path, monkeypatch, patch_modeld):
-    from openpilot.common.hardware import hw
-    from openpilot.selfdrive.modeld.helpers import dump_oob
-    shapes = {'img': (1, 12, 128, 256), 'big_img': (1, 12, 128, 256), 'features_buffer': (1, 24, 32, 512),
-              'desire_pulse': (1, 25, 8), 'traffic_convention': (1, 2), 'action_t': (1, 2)}
-    pkl_data = {'metadata': {'model': {'input_shapes': shapes, 'output_slices': {}}},
-                'run_model': {(CAM_W, CAM_H): tests_helpers._noop_jit}}
-    with open(tmp_path / 'driving_test_tinygrad.pkl', 'wb') as f:
-      dump_oob(pkl_data, f)
-    bundle = DummyBundle(models=[DummyModel('supercombo', 'driving_test_tinygrad.pkl')])
-    patch_modeld(bundle)
-    monkeypatch.setattr(hw.Paths, 'model_root', staticmethod(lambda: str(tmp_path)))
-    state = ModelState(cam_w=CAM_W, cam_h=CAM_H)
-    assert state.is_run_model and state.run_model is not None
-    assert state.run_policy is None and state.warp is None
-    assert 'img' in state.frame_views and 'big_img' in state.frame_views
-
 
 ARCHETYPE_NAMES = list(ARCHETYPES.keys())
 

openpilot/sunnypilot/models/fetcher.py

@@ -139,7 +139,7 @@ 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_v22.json"
-  MODEL_URL_CHESTNUT = "https://raw.githubusercontent.com/sunnypilot/sunnypilot-models/refs/heads/gh-pages/docs/driving_models_chestnut_v25.json"
+  MODEL_URL_CHESTNUT = "https://raw.githubusercontent.com/sunnypilot/sunnypilot-models/refs/heads/gh-pages/docs/driving_models_chestnut_v23.json"
 
   MODEL_SOURCES = {
     "qcom": (MODEL_URL, ""),

openpilot/sunnypilot/sunnylink/settings_ui.json

@@ -1675,6 +1675,12 @@
               "widget": "toggle",
               "title": "Onroad Uploads"
             },
+            {
+              "key": "AuxPowerSave",
+              "widget": "toggle",
+              "title": "Disable Aux Port When Offroad",
+              "description": "Power off the aux USB-C port while offroad to save power. It powers back on automatically when you go onroad."
+            },
             {
               "key": "MaxTimeOffroad",
               "widget": "option",

openpilot/sunnypilot/sunnylink/settings_ui_src/pages/device.yaml

@@ -30,6 +30,10 @@ sections:
   - key: OnroadUploads
     widget: toggle
     title: Onroad Uploads
+  - key: AuxPowerSave
+    widget: toggle
+    title: Disable Aux Port When Offroad
+    description: Power off the aux USB-C port while offroad to save power. It powers back on automatically when you go onroad.
   - key: MaxTimeOffroad
     widget: option
     title: Max Time Offroad

openpilot/system/hardware/hardwared.py

@@ -21,6 +21,7 @@ from openpilot.common.hardware import HARDWARE, COMMA_HARDWARE
 from openpilot.common.basedir import BASEDIR
 from openpilot.common.git import get_short_branch
 from openpilot.common.hardware.usb import CHESTNUT_FW_VERSION, CHESTNUT_USB_PRODUCT, get_usb_state, get_usb_topology, is_chestnut_usb_id, set_usb_state
+from openpilot.system.hardware.chestnut.flash import VBUS_PATH
 from openpilot.common.linux import LinuxSystemStats
 from openpilot.system.loggerd.config import get_available_percent
 from openpilot.common.swaglog import cloudlog
@@ -50,6 +51,10 @@ class Chestnut:
     self.last_attempt = 0.
     self.flashed = False
     self.mismatch = False
+    self.vbus_on = None
+    self.params = Params()
+    self.powersave = False
+    self.last_offroad = None
 
   @property
   def failed(self) -> bool:
@@ -61,9 +66,19 @@ class Chestnut:
     cloudlog.event("chestnut flash done", returncode=ret.returncode, output=ret.stdout[-1000:], error=ret.returncode != 0)
     self.flashed = ret.returncode == 0
 
+  def set_vbus(self, on: bool) -> None:
+    if on == self.vbus_on:
+      return
+    subprocess.run(["sudo", "tee", VBUS_PATH], input=b"1" if on else b"0", stdout=subprocess.DEVNULL, check=False)
+    self.vbus_on = on
+
   def update(self, offroad: bool, usb_state: list[dict]) -> None:
     self.mismatch = any(is_chestnut_usb_id(d["vendorId"], d["productId"], include_bootloader=True) and
                         d["product"] != CHESTNUT_USB_PRODUCT for d in usb_state)
+    if offroad != self.last_offroad:
+      self.powersave = self.params.get_bool("AuxPowerSave")
+      self.last_offroad = offroad
+    self.set_vbus((not offroad or self.mismatch) or not self.powersave)
     if not self.mismatch:
       self.flashed = False
       return