ci: route build_model runner by hardware type

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

@@ -121,7 +121,7 @@ jobs:
           if-no-files-found: error
 
   build_model:
-    runs-on: [self-hosted, chestnut]
+    runs-on: [self-hosted, "${{ inputs.target_hardware == 'chestnut' && 'chestnut' || 'tici' }}"]
     needs: get_model
     env:
       MODEL_NAME: ${{ inputs.custom_name || inputs.upstream_branch }} (${{ needs.get_model.outputs.model_date }})

openpilot/common/params_keys.h

@@ -132,7 +132,6 @@ inline static std::unordered_map<std::string, ParamKeyAttributes> keys = {
     {"UptimeOnroad", {PERSISTENT, FLOAT, "0.0"}},
     {"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}},
-    {"AuxPowerSave", {PERSISTENT | BACKUP, BOOL}},
     {"Version", {PERSISTENT, STRING}},
 
     // --- sunnypilot params --- //

openpilot/selfdrive/ui/ui_state.py

@@ -220,7 +220,6 @@ 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/modeld.py

@@ -8,22 +8,22 @@ See the LICENSE.md file in the root directory for more details.
 
 import os
 os.environ['GMMU'] = '0'
+import numpy as np
+import threading
+import time
+from setproctitle import setproctitle
+from tinygrad.tensor import Tensor
+
+import openpilot.cereal.messaging as messaging
 from openpilot.common.hardware import COMMA_HARDWARE
 from openpilot.selfdrive.modeld.helpers import chestnut_present, load_oob
-import time
-import numpy as np
-import openpilot.cereal.messaging as messaging
 from openpilot.cereal import log
 from opendbc.car.structs import car
 from openpilot.cereal.services import SERVICE_LIST
-from setproctitle import setproctitle
 from openpilot.cereal.messaging import PubMaster, SubMaster
 from openpilot.cereal.visionipc import VisionStreamType
 from msgq.visionipc import VisionIpcClient, VisionBuf
 from opendbc.car.car_helpers import get_demo_car_params
-
-from tinygrad.tensor import Tensor
-
 from openpilot.common.file_chunker import open_file_chunked
 from openpilot.common.swaglog import cloudlog
 from openpilot.common.params import Params
@@ -42,13 +42,13 @@ 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, 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
 from openpilot.sunnypilot.selfdrive.controls.lib.relc import RoadEdgeLaneChangeController
 
 PROCESS_NAME = "openpilot.selfdrive.modeld.modeld_tinygrad"
+BIG_MODEL_TIMEOUT = 60
 
 
 def _pkl_exists(path):
@@ -68,6 +68,7 @@ def _find_driving_pkl(bundle):
   pkl_path = os.path.join(model_root, pkl_name)
   if _pkl_exists(pkl_path):
     return pkl_path
+  return None
 
 
 class FrameMeta:
@@ -102,7 +103,7 @@ class ModelState(ModelStateBase):
     self.chestnut = chestnut
 
     pkl_path = _find_driving_pkl(model_bundle)
-    assert pkl_path is not None, "No driving pkl found — all models must be compiled with compile_modeld.py"
+    assert pkl_path is not None, f"No driving pkl found for {'chestnut' if chestnut else 'small model'} — all models must be compiled with compile_modeld.py"
     self._init_combined(pkl_path, cam_w, cam_h, model_bundle)
 
   def _init_combined(self, pkl_path, cam_w, cam_h, bundle):
@@ -185,9 +186,6 @@ class ModelState(ModelStateBase):
     else:
       self.warp(**{k: self.input_queues[k] for k in WARP_INPUTS}, frame=frame_tensor, big_frame=big_frame_tensor)
 
-    if self.chestnut:
-      self.warmup()
-
   def warmup(self) -> None:
     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}
@@ -288,8 +286,7 @@ class ModelState(ModelStateBase):
       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.])))):
-      cloudlog.error("model output not finite, dropping frame")
+      raise RuntimeError("model output not finite")
-      return None
 
     return outputs
 
@@ -363,21 +360,26 @@ def main(demo=False):
 
   model = None
   if CHESTNUT:
-    import threading
+    big_model = None
-    def load():
+    def load_big():
-      nonlocal model
+      nonlocal big_model
-      model = ModelState(cam_w=vipc_client_main.width, cam_h=vipc_client_main.height, chestnut=True)
+      try:
-    t = threading.Thread(target=load, daemon=True)
+        m = ModelState(cam_w=vipc_client_main.width, cam_h=vipc_client_main.height, chestnut=True)
-    t.start()
+        m.warmup()
-    t.join(60)
+        big_model = m
-    if model is None:
+      except Exception:
-      params.put_bool("ChestnutActive", False)
+        cloudlog.exception("chestnut load failed")
-      raise RuntimeError("chestnut model load failed or timed out (60s)")
+    loader = threading.Thread(target=load_big, daemon=True)
-    params.put_bool("ChestnutActive", True)
+    loader.start()
-  else:
+    loader.join(BIG_MODEL_TIMEOUT)
-    model = ModelState(cam_w=vipc_client_main.width, cam_h=vipc_client_main.height, chestnut=False)
+    model = big_model
+    params.put_bool("ChestnutActive", model is not None)
 
+  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:
+    model = small_model
   params.put_bool("ChestnutLoading", False)
+  assert model is not None
   cloudlog.warning(f"models loaded in {time.monotonic() - st:.1f}s, modeld starting")
 
   # messaging
@@ -386,7 +388,7 @@ def main(demo=False):
   sm = SubMaster(["deviceState", "carState", "narrowRoadCameraState", "extrinsicsCalibration", "driverMonitoringState", "carControl", "lateralDelay"])
 
   publish_state = PublishState()
-  chestnut_state = ChestnutState(pm, CHESTNUT) if CHESTNUT else None
+  chestnut_state = ChestnutState(pm, model.chestnut) if CHESTNUT else None
 
   # setup filter to track dropped frames
   frame_dropped_filter = FirstOrderFilter(0., 10., 1. / model.constants.MODEL_FREQ)
@@ -509,7 +511,19 @@ def main(demo=False):
       inputs['action_t'] = np.array([lat_action_t, long_action_t], dtype=np.float32)
 
     mt1 = time.perf_counter()
-    model_output = model.run(bufs, transforms, inputs, prepare_only)
+    try:
+      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("ChestnutActive", False)
+      assert small_model is not None
+      model = small_model
+      if chestnut_state is not None:
+        chestnut_state.big = False
+      run_count = 0
+      model_output = None
     mt2 = time.perf_counter()
     model_execution_time = mt2 - mt1
 

openpilot/sunnypilot/modeld_v2/tests/test_fallback.py

@@ -0,0 +1,62 @@
+"""
+Copyright (c) 2021-, Haibin Wen, sunnypilot, and a number of other contributors.
+
+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.
+"""
+
+import io
+import requests
+
+from openpilot.common.file_chunker import get_chunk_name
+from openpilot.common.hardware import hw
+from openpilot.common.test import OpenpilotTestCase
+from openpilot.selfdrive.modeld.helpers import dump_oob
+import openpilot.sunnypilot.modeld_v2.modeld as modeld_module
+from openpilot.sunnypilot.modeld_v2.tests import helpers as tests_helpers
+from openpilot.sunnypilot.modeld_v2.tests.helpers import DummyModel, DummyBundle, CAM_W, CAM_H
+from openpilot.sunnypilot.models.fetcher import ModelParser, ModelFetcher
+
+tmp_path = tests_helpers.tmp_path
+
+
+class TestFallback(OpenpilotTestCase):
+  def test_find_dual_model_in_bundle(self, tmp_path, monkeypatch):
+    lebowski_file = 'driving_lebowski.pkl'
+    tsfdo_file = 'driving_tsfdo.pkl'
+    (tmp_path / lebowski_file).write_bytes(b'fkasdjfkljf')
+    (tmp_path / tsfdo_file).write_bytes(b'dskfajklsdjlsfka')
+
+    monkeypatch.setattr(hw.Paths, 'model_root', staticmethod(lambda: str(tmp_path)))
+    big_bundle = DummyBundle(models=[DummyModel('supercombo', lebowski_file)])
+    small_bundle = DummyBundle(models=[DummyModel('supercombo', tsfdo_file)])
+    big_pkl = modeld_module._find_driving_pkl(big_bundle)
+    small_pkl = modeld_module._find_driving_pkl(small_bundle)
+
+    assert big_pkl is not None and lebowski_file in big_pkl
+    assert small_pkl is not None and tsfdo_file in small_pkl
+
+  def test_download_models_and_init_modelstate_fallback(self, tmp_path, monkeypatch):
+    monkeypatch.setattr(hw.Paths, 'model_root', staticmethod(lambda: str(tmp_path)))
+    big_json = requests.get(ModelFetcher.MODEL_URL_CHESTNUT).json()
+    big_bundle = ModelParser.parse_models(big_json)[-1]
+    small_json = requests.get(ModelFetcher.MODEL_URL).json()
+    small_bundle = ModelParser.parse_models(small_json)[-1]
+
+    buf = io.BytesIO()
+    dump_oob(tests_helpers.make_pkl_data(tests_helpers.ARCHETYPES['supercombo_non20hz']), buf)
+    oob_bytes = buf.getvalue()
+
+    for bundle in (big_bundle, small_bundle):
+      artifact = bundle.models[0].artifact
+      for i in range(len(artifact.chunks)):
+        (tmp_path / get_chunk_name(artifact.fileName, i, len(artifact.chunks))).write_bytes(oob_bytes if i == 0 else b"")
+
+    monkeypatch.setattr(modeld_module, 'get_active_bundle', lambda params=None, *, chestnut=None: small_bundle)
+    assert modeld_module.ModelState(CAM_W, CAM_H, chestnut=False).chestnut is False
+
+    monkeypatch.setattr(modeld_module, 'get_active_bundle', lambda params=None, *, chestnut=None: big_bundle)
+    try:
+      assert modeld_module.ModelState(CAM_W, CAM_H, chestnut=True).chestnut is True
+    except Exception as e:
+      assert "AMD" in str(e) or "device" in str(e).lower()

openpilot/sunnypilot/models/default_model.py

@@ -1,11 +1,14 @@
 import argparse
 import os
 import hashlib
+import requests
+import re
 
 from openpilot.common.basedir import BASEDIR
 from openpilot.selfdrive.ui.ui_state import ui_state
 from openpilot.sunnypilot import get_file_hash
 from openpilot.sunnypilot.models.model_name import DEFAULT_MODEL, DEFAULT_BIG_MODEL
+from openpilot.sunnypilot.models.fetcher import ModelFetcher
 
 
 def get_default_model() -> str:
@@ -30,14 +33,29 @@ def update_model_hash():
   print(f"Generated and updated new combined model hash to {MODEL_HASH_PATH}")
 
 
+def get_ref_for_name(url: str, name: str) -> str:
+  response = requests.get(url, timeout=10)
+  if response.status_code == 200:
+    bundles = response.json()["bundles"]
+    matching = [b for b in bundles if re.search(name, f"{b['short_name']} {b['display_name']}", re.IGNORECASE)]
+    if matching:
+      return max(matching, key=lambda b: int(b["index"]))["ref"]
+  return ""
+
+
 def update_default_model_names(default_model_name: str, default_big_model_name: str):
   print("[CHANGE DEFAULT MODEL NAMES]")
+  small_ref = get_ref_for_name(ModelFetcher.MODEL_URL, default_model_name)
+  big_ref = get_ref_for_name(ModelFetcher.MODEL_URL_CHESTNUT, default_big_model_name)
+
   with open(DEFAULT_MODEL_NAME_PATH, "w") as f:
     f.write(f'DEFAULT_MODEL = "{default_model_name}"\n')
+    f.write(f'DEFAULT_MODEL_REF = "{small_ref}"\n')
     f.write(f'DEFAULT_BIG_MODEL = "{default_big_model_name}"\n')
+    f.write(f'DEFAULT_BIG_MODEL_REF = "{big_ref}"\n')
 
-  print(f'New default small model name: "{default_model_name}"')
+  print(f'New default small model name: "{default_model_name}" (ref: {small_ref})')
-  print(f'New default big model name: "{default_big_model_name}"')
+  print(f'New default big model name: "{default_big_model_name}" (ref: {big_ref})')
   print("[DONE]")
 
 

openpilot/sunnypilot/models/manager.py

@@ -328,6 +328,12 @@ class ModelManagerSP:
         validate_active_bundles(self.params, self.source_models)
         self.active_bundle = get_active_bundle(self.params, chestnut=self.chestnut_present)
 
+        if get_selected_bundle(self.params, "chestnut") is not None and get_selected_bundle(self.params, "qcom") is None:
+          if self.params.get("ModelManager_DownloadRef") is None:
+            from openpilot.sunnypilot.models.model_name import DEFAULT_MODEL_REF
+            if DEFAULT_MODEL_REF:
+              self.params.put("ModelManager_DownloadRef", DEFAULT_MODEL_REF)
+
         self._process_download_requests()
 
         if self.params.get("ModelManager_ClearCache"):

openpilot/sunnypilot/models/model_name.py

@@ -1,2 +1,4 @@
 DEFAULT_MODEL = "CD210"
+DEFAULT_MODEL_REF = "5b6436a90cf6902b8aaa71c2b6f3d7164d8ae391"
 DEFAULT_BIG_MODEL = "Lebowski"
+DEFAULT_BIG_MODEL_REF = "fa0c6876d3cf070e91e25e5353ceadc68a5b3285"

openpilot/sunnypilot/sunnylink/settings_ui.json

@@ -1675,12 +1675,6 @@
               "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

@@ -30,10 +30,6 @@ 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

@@ -21,7 +21,6 @@ from openpilot.selfdrive.selfdrived.alertmanager import set_offroad_alert
 from openpilot.common.hardware import HARDWARE, COMMA_HARDWARE
 from openpilot.common.basedir import BASEDIR
 from openpilot.common.hardware.usb import CHESTNUT_FW_VERSION, CHESTNUT_ROM_USB_IDS, CHESTNUT_USB_IDS, get_usb_state, get_usb_topology, 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
@@ -50,10 +49,6 @@ class Chestnut:
     self.attempts = 0
     self.last_attempt = 0.
     self.flashed = False
-    self.vbus_on = None
-    self.params = Params()
-    self.powersave = False
-    self.last_offroad = None
 
   def flash(self) -> None:
     ret = subprocess.run(["sudo", sys.executable, os.path.join(BASEDIR, "openpilot/system/hardware/chestnut/flash.py"), CHESTNUT_FW_VERSION],
@@ -61,19 +56,9 @@ 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:
     mismatch = any((d["vendorId"], d["productId"]) in CHESTNUT_USB_IDS + CHESTNUT_ROM_USB_IDS and
                    d["product"] != f"custom {CHESTNUT_FW_VERSION}-CLEAN" 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 mismatch) or not self.powersave)
     if not mismatch:
       self.flashed = False
       return