debug

* models: self healing test for tg

* rm container

* ew

* set env

* set var

.github/workflows/test_models.yml

@@ -3,9 +3,62 @@ on:
   pull_request:
     paths:
       - 'tinygrad_repo'
+      - 'openpilot/sunnypilot/modeld_v2/**'
   workflow_dispatch:
 
+env:
+  CI: 1
+  GIT_CONFIG_COUNT: 1
+  GIT_CONFIG_KEY_0: lfs.fetchexclude
+  GIT_CONFIG_VALUE_0: openpilot/selfdrive/modeld/models/big_driving_tinygrad.pkl
+
 jobs:
+  plain-artifact:
+    name: Plain artifact round trip and pickle converter
+    runs-on: ubuntu-24.04
+    env:
+      PYTHONPATH: ${{ github.workspace }}/tinygrad_repo:${{ github.workspace }}
+      TINYGRAD_TESTS: 1
+    steps:
+      - uses: actions/checkout@v7
+      - run: ./tools/op.sh setup
+      - name: Build openpilot
+        run: scons -j$(nproc)
+      - name: Compile, load, cache and fuse a model with the pinned tinygrad
+        env:
+          DEV: CPU
+        run: tools/op.sh test -v openpilot/sunnypilot/modeld_v2/tests/test_plain_artifact.py
+      - name: Install LLVM 20 and ROCm comgr for the amd mock, as tinygrad_repo/.github/actions/setup-tinygrad does
+        run: |
+          . /etc/os-release
+          curl -fsSL https://apt.llvm.org/llvm-snapshot.gpg.key | sudo tee /etc/apt/trusted.gpg.d/apt.llvm.org.asc > /dev/null
+          echo "deb http://apt.llvm.org/$VERSION_CODENAME/ llvm-toolchain-$VERSION_CODENAME-20 main" | sudo tee /etc/apt/sources.list.d/llvm.list
+          sudo mkdir -p /etc/apt/keyrings
+          curl -fsSL https://repo.radeon.com/rocm/rocm.gpg.key | gpg --dearmor | sudo tee /etc/apt/keyrings/rocm.gpg > /dev/null
+          echo "deb [arch=amd64 signed-by=/etc/apt/keyrings/rocm.gpg] https://repo.radeon.com/rocm/apt/7.1 $VERSION_CODENAME main" | sudo tee /etc/apt/sources.list.d/rocm.list
+          printf 'Package: *\nPin: release o=repo.radeon.com\nPin-Priority: 600\n' | sudo tee /etc/apt/preferences.d/rocm-pin-600
+          sudo apt-get -qq update && sudo apt-get -qq install -y --no-install-recommends libllvm20 clang-20 lld-20 comgr
+          printf '/opt/rocm/lib\n/opt/rocm/lib64\n' | sudo tee /etc/ld.so.conf.d/rocm.conf && sudo ldconfig
+          echo "/usr/lib/llvm-20/bin" >> "$GITHUB_PATH"
+      - name: Convert a pickled USB+AMD jit and replay it under tinygrad's amd mock
+        env:
+          DEV: MOCKUSB+AMD
+          CHECK_OOB: 0
+          GMMU: 0
+        run: tools/op.sh test -v openpilot/sunnypilot/modeld_v2/tests/test_convert_upstream_pkl.py
+      - name: Where tinygrad moved, for the helper or failure point named above
+        if: failure() && github.event_name == 'pull_request'
+        run: |
+          git fetch -q --depth=1 origin "${{ github.base_ref }}"
+          old=$(git rev-parse "origin/${{ github.base_ref }}:tinygrad_repo") new=$(git rev-parse HEAD:tinygrad_repo)
+          git -C tinygrad_repo fetch -q origin "$old" || true
+          echo "tinygrad_repo $old -> $new, in what helpers.py and plain_artifact_compiler.py read:"
+          git -C tinygrad_repo diff "$old" "$new" -- tinygrad/uop/ops.py tinygrad/engine/jit.py tinygrad/engine/realize.py tinygrad/device.py \
+            tinygrad/helpers.py tinygrad/dtype.py tinygrad/renderer/__init__.py
+          echo "and in what convert_upstream_pkl.py decodes:"
+          git -C tinygrad_repo diff --stat "$old" "$new" -- tinygrad/runtime/autogen/am/pm4_nv.py tinygrad/runtime/autogen/amd_gpu.py
+          git -C tinygrad_repo diff "$old" "$new" -- tinygrad/runtime/support/hcq2.py tinygrad/runtime/support/usb.py tinygrad/runtime/ops_amd.py
+
   generate-matrix:
     runs-on: ubuntu-latest
     outputs:

openpilot/cereal/custom.capnp

@@ -138,6 +138,9 @@ struct ModelManagerSP @0xaedffd8f31e7b55d {
     status @0 :DownloadStatus;
     progress @1 :Float32;
     eta @2 :UInt32;
+    speed @3 :Float32;
+    canceling @4 :Bool;
+    resuming @5 :Bool;
   }
 
   struct Chunk {

openpilot/common/params_keys.h

@@ -170,6 +170,7 @@ inline static std::unordered_map<std::string, ParamKeyAttributes> keys = {
     {"DevUIInfo", {PERSISTENT | BACKUP, INT, "0"}},
     {"EnableCopyparty", {PERSISTENT | BACKUP, BOOL}},
     {"EnableGithubRunner", {PERSISTENT | BACKUP, BOOL}},
+    {"FollowDistanceAccelBoost", {PERSISTENT | BACKUP, BOOL, "0"}},
     {"GreenLightAlert", {PERSISTENT | BACKUP, BOOL, "0"}},
     {"GithubRunnerSufficientVoltage", {CLEAR_ON_MANAGER_START , BOOL}},
     {"HasAcceptedTermsSP", {PERSISTENT, STRING, "0"}},

openpilot/selfdrive/controls/tests/test_accel_boost.py

@@ -0,0 +1,101 @@
+from types import SimpleNamespace
+
+from openpilot.cereal import log
+from openpilot.common.realtime import DT_MDL
+from openpilot.common.test import OpenpilotTestCase
+from openpilot.selfdrive.controls.lib.accel_boost import (
+  AccelBoost, ACCEL_BOOST_MAX, ACCEL_BOOST_PER_OVERRIDE, ACCEL_BOOST_RATE
+)
+
+E2E_ACCEL = 0.5
+PLANNER_ACCEL = 2.0
+RATE_PER_STEP = ACCEL_BOOST_RATE * DT_MDL
+
+
+class FakeSubMaster:
+  def __init__(self, enabled=True, gas_pressed=False, v_ego=15.0,
+               personality=log.LongitudinalPersonality.standard):
+    self._messages = {
+      'selfdriveState': SimpleNamespace(enabled=enabled, personality=personality),
+      'carState': SimpleNamespace(gasPressed=gas_pressed, vEgo=v_ego),
+    }
+
+  def __getitem__(self, key):
+    return self._messages[key]
+
+
+def run_boost(boost, sm, steps=1):
+  out = E2E_ACCEL
+  for _ in range(steps):
+    out = boost.update(sm, E2E_ACCEL, PLANNER_ACCEL, PLANNER_ACCEL)
+  return out
+
+
+class TestAccelBoost(OpenpilotTestCase):
+  def _boost_to_max(self):
+    boost = AccelBoost()
+    sm = FakeSubMaster()
+    steps = round(ACCEL_BOOST_PER_OVERRIDE / RATE_PER_STEP)
+    # Eligibility is latched on a frame without gas, then applied on the next override.
+    run_boost(boost, sm)
+    for _ in range(10):
+      sm['carState'].gasPressed = True
+      run_boost(boost, sm, steps)
+      sm['carState'].gasPressed = False
+      run_boost(boost, sm)
+    return boost
+
+  def test_no_boost_without_gas(self):
+    boost = AccelBoost()
+    sm = FakeSubMaster(gas_pressed=False)
+    out = run_boost(boost, sm)
+    self.assertEqual(boost.total_boost, 0.0)
+    self.assertAlmostEqual(out, E2E_ACCEL)
+
+  def test_boost_requires_e2e_to_be_limiting(self):
+    boost = AccelBoost()
+    sm = FakeSubMaster(gas_pressed=False)
+    # Eligibility is latched before the override, so keep the e2e plan at the planner limit here.
+    boost.update(sm, E2E_ACCEL, E2E_ACCEL, E2E_ACCEL)
+    sm['carState'].gasPressed = True
+    for _ in range(10):
+      boost.update(sm, E2E_ACCEL, E2E_ACCEL, E2E_ACCEL)
+    self.assertEqual(boost.total_boost, 0.0)
+
+  def test_per_override_cap(self):
+    boost = AccelBoost()
+    sm = FakeSubMaster(gas_pressed=False)
+    run_boost(boost, sm)
+    sm['carState'].gasPressed = True
+    run_boost(boost, sm, 1000)
+    self.assertAlmostEqual(boost.total_boost, ACCEL_BOOST_PER_OVERRIDE)
+
+  def test_max_boost(self):
+    boost = self._boost_to_max()
+    self.assertAlmostEqual(boost.total_boost, ACCEL_BOOST_MAX)
+
+  def test_boost_is_applied_to_e2e_accel(self):
+    boost = self._boost_to_max()
+    sm = FakeSubMaster(gas_pressed=True)
+    out = run_boost(boost, sm)
+    self.assertAlmostEqual(out, E2E_ACCEL + boost.total_boost)
+
+  def test_boost_does_not_depend_on_following_distance(self):
+    totals = []
+    for personality in (log.LongitudinalPersonality.relaxed,
+                        log.LongitudinalPersonality.standard,
+                        log.LongitudinalPersonality.aggressive):
+      boost = AccelBoost()
+      sm = FakeSubMaster(personality=personality)
+      steps = round(ACCEL_BOOST_PER_OVERRIDE / RATE_PER_STEP)
+      run_boost(boost, sm)
+      for _ in range(10):
+        sm['carState'].gasPressed = True
+        run_boost(boost, sm, steps)
+        sm['carState'].gasPressed = False
+        run_boost(boost, sm)
+      totals.append(boost.total_boost)
+
+    self.assertEqual(len(totals), 3)
+    for total in totals:
+      self.assertAlmostEqual(total, ACCEL_BOOST_MAX)

openpilot/selfdrive/ui/mici/layouts/settings/toggles.py

@@ -21,6 +21,9 @@ class TogglesLayoutMici(NavScroller):
                                                                "Use the steering wheel distance button on supported cars.")
     self._initial_cruise_speed = InitialCruiseSpeedButton()
     self._initial_cruise_speed.set_visible(lambda: ui_state.CP is not None and ui_state.has_longitudinal_control and not ui_state.CP.pcmCruise)
+    self._accel_boost_toggle = BigParamControl("extra acceleration boost", "FollowDistanceAccelBoost",
+                                               description="Adds extra acceleration on top of the stock gas-override boost.\n" +
+                                                           "The extra boost follows Following Distance: strongest when Aggressive, weakest when Relaxed.")
     is_metric_toggle = BigToggle("use metric units", initial_state=ui_state.params.get_bool("IsMetric"), toggle_callback=self._on_metric_toggle)
     ldw_toggle = BigParamControl("lane departure warnings", "IsLdwEnabled",
                                  description="Warn when you drift across a detected lane line.\n" +
@@ -40,6 +43,7 @@ class TogglesLayoutMici(NavScroller):
 
     self._scroller.add_widgets([
       self._personality_toggle,
+      self._accel_boost_toggle,
       self._initial_cruise_speed,
       is_metric_toggle,
       ldw_toggle,
@@ -51,6 +55,7 @@ class TogglesLayoutMici(NavScroller):
 
     # Toggle lists
     self._refresh_toggles = (
+      ("FollowDistanceAccelBoost", self._accel_boost_toggle),
       ("IsMetric", is_metric_toggle),
       ("IsLdwEnabled", ldw_toggle),
       ("AlwaysOnDM", always_on_dm_toggle),
@@ -92,6 +97,7 @@ class TogglesLayoutMici(NavScroller):
 
     if ui_state.CP is not None:
       self._personality_toggle.set_visible(ui_state.has_longitudinal_control)
+      self._accel_boost_toggle.set_visible(ui_state.has_longitudinal_control)
 
     # Refresh toggles from params to mirror external changes
     for key, item in self._refresh_toggles:

openpilot/selfdrive/ui/mici/onroad/accel_boost_indicator.py

@@ -0,0 +1,141 @@
+"""
+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 pyray as rl
+
+from openpilot.cereal import log
+from openpilot.common.filter_simple import FirstOrderFilter
+from openpilot.selfdrive.ui.mici.onroad import SIDE_PANEL_WIDTH
+from openpilot.selfdrive.ui.ui_state import ui_state
+from openpilot.system.ui.lib.application import FontWeight, gui_app
+from openpilot.system.ui.lib.text_measure import measure_text_cached
+from openpilot.system.ui.widgets import Widget
+from openpilot.sunnypilot.selfdrive.controls.lib.accel_boost_ext import get_accel_boost_max
+
+# The readout is wider than the side panel, so the value is right-aligned and bleeds over the camera view
+BAR_WIDTH = 24
+# Fades to white only near the profile cap, like the stock torque bar fading toward orange at high torque
+CAP_BLEND_START = 0.75
+MAX_BOOST_BLEND = 0.45
+
+COLOR_TRACK = rl.Color(255, 255, 255, 45)
+COLOR_TRACK_EDGE = rl.Color(255, 255, 255, 70)
+COLOR_TEXT = rl.Color(255, 255, 255, 235)
+COLOR_TEXT_SHADOW = rl.Color(0, 0, 0, 150)
+
+# Temporary debug readout next to the bar, flip off once the bar alone reads right
+SHOW_VALUE = True
+VALUE_FONT_SIZE = 24
+
+AGGRESSIVE_COLOR = rl.Color(255, 80, 60, 255)
+STANDARD_COLOR = rl.Color(0, 230, 120, 255)
+RELAXED_COLOR = rl.Color(70, 150, 255, 255)
+
+FADE_THRESHOLD = 0.01
+
+
+def lighten(color: rl.Color, amount: float) -> rl.Color:
+  """Lerp towards white in RGB, so the hue stays put the way HSV blending would not."""
+  amount = min(max(amount, 0.0), 1.0)
+  return rl.Color(int(color.r + (255 - color.r) * amount),
+                  int(color.g + (255 - color.g) * amount),
+                  int(color.b + (255 - color.b) * amount), color.a)
+
+
+def get_boost_fraction(boost: float, max_boost: float) -> float:
+  """How much of the active profile's boost budget is in use, clamped to a full bar."""
+  if max_boost <= 0.0:
+    return 0.0
+  return min(max(boost / max_boost, 0.0), 1.0)
+
+
+def get_boost_style(personality) -> tuple[rl.Color, float]:
+  if personality == log.LongitudinalPersonality.aggressive:
+    color = AGGRESSIVE_COLOR
+  elif personality == log.LongitudinalPersonality.relaxed:
+    color = RELAXED_COLOR
+  else:
+    color = STANDARD_COLOR
+
+  return color, get_accel_boost_max(personality)
+
+
+class AccelBoostIndicator(Widget):
+  def __init__(self):
+    super().__init__()
+    self._boost_filter = FirstOrderFilter(0.0, 0.15, 1 / gui_app.target_fps)
+    self._alpha_filter = FirstOrderFilter(0.0, 0.1, 1 / gui_app.target_fps)
+    # Smoothly rescale the bar when the follow distance profile changes mid-drive
+    self._max_boost_filter = FirstOrderFilter(0.0, 0.25, 1 / gui_app.target_fps)
+    self._font = gui_app.font(FontWeight.BOLD)
+    self._profile_color = STANDARD_COLOR
+    self._max_boost = 0.0
+
+    self.panel_in_use = False
+
+  def _update_state(self):
+    sm = ui_state.sm
+    extra_enabled = ui_state.follow_distance_accel_boost
+    visible = (ui_state.has_longitudinal_control and sm.alive['selfdriveState'] and sm.alive['longitudinalPlan'] and
+               sm['selfdriveState'].enabled)
+    self._alpha_filter.update(1.0 if visible and extra_enabled else 0.0)
+    self._boost_filter.update(float(sm['longitudinalPlan'].accelBoost) if visible else 0.0)
+
+    if sm.alive['selfdriveState']:
+      self._profile_color, self._max_boost = get_boost_style(sm['selfdriveState'].personality)
+    self._max_boost_filter.update(self._max_boost)
+
+    self.panel_in_use = extra_enabled and ui_state.has_longitudinal_control
+
+  def _render(self, _):
+    alpha = self._alpha_filter.x
+    if alpha < FADE_THRESHOLD or self._max_boost <= 0.0:
+      return
+
+    cx = self.rect.x + self.rect.width - SIDE_PANEL_WIDTH / 2
+    bar_x = cx - BAR_WIDTH / 2
+    track_top = self.rect.y + self.rect.height * 0.08
+    track_bottom = self.rect.y + self.rect.height * 0.92
+    track_h = max(1.0, track_bottom - track_top)
+
+    # track, light enough to read on the black side panel
+    rl.draw_rectangle_rounded(rl.Rectangle(bar_x, track_top, BAR_WIDTH, track_h), 0.5, 12,
+                              rl.Color(COLOR_TRACK.r, COLOR_TRACK.g, COLOR_TRACK.b, int(COLOR_TRACK.a * alpha)))
+    rl.draw_rectangle_rounded_lines_ex(rl.Rectangle(bar_x, track_top, BAR_WIDTH, track_h), 0.5, 12, 1,
+                                       rl.Color(COLOR_TRACK_EDGE.r, COLOR_TRACK_EDGE.g, COLOR_TRACK_EDGE.b,
+                                                int(COLOR_TRACK_EDGE.a * alpha)))
+
+    # Scale to the current profile's cap, so a maxed boost fills the bar and a profile change rescales it
+    boost = max(self._boost_filter.x, 0.0)
+    ratio = get_boost_fraction(boost, self._max_boost_filter.x)
+    fill_h = ratio * track_h
+    cap_blend = max(0.0, (ratio - CAP_BLEND_START) / (1.0 - CAP_BLEND_START))
+    fill_color = lighten(self._profile_color, MAX_BOOST_BLEND * cap_blend)
+    if fill_h > 0.0:
+      # soft glow around the tip, like the confidence ball's gradient
+      tip_y = track_bottom - fill_h
+      glow = rl.Color(fill_color.r, fill_color.g, fill_color.b, int(70 * alpha))
+      rl.draw_circle_gradient(rl.Vector2(cx, tip_y), int(BAR_WIDTH * 0.9), glow, rl.BLANK)
+
+      fill = rl.Color(fill_color.r, fill_color.g, fill_color.b, int(255 * alpha))
+      if fill_h < BAR_WIDTH:
+        rl.draw_circle(int(cx), int(track_bottom - fill_h / 2), max(1, int(BAR_WIDTH / 2)), fill)
+      else:
+        rl.draw_rectangle_rounded(rl.Rectangle(bar_x, track_bottom - fill_h, BAR_WIDTH, fill_h), 0.5, 12, fill)
+
+    if SHOW_VALUE:
+      value = f"+{boost:.2f}"
+      value_size = measure_text_cached(self._font, value, VALUE_FONT_SIZE)
+      value_pos = rl.Vector2(bar_x - 8 - value_size.x, (track_top + track_bottom) / 2 - value_size.y / 2)
+      self._draw_text(self._font, value, value_pos, VALUE_FONT_SIZE,
+                      rl.Color(COLOR_TEXT.r, COLOR_TEXT.g, COLOR_TEXT.b, int(COLOR_TEXT.a * alpha)))
+
+  @staticmethod
+  def _draw_text(font, text: str, pos: rl.Vector2, font_size: int, color: rl.Color) -> None:
+    # Drop shadow keeps the readout legible against the camera feed
+    shadow = rl.Color(COLOR_TEXT_SHADOW.r, COLOR_TEXT_SHADOW.g, COLOR_TEXT_SHADOW.b, int(COLOR_TEXT_SHADOW.a * color.a / 255))
+    rl.draw_text_ex(font, text, rl.Vector2(pos.x + 1, pos.y + 1), font_size, 0, shadow)
+    rl.draw_text_ex(font, text, pos, font_size, 0, color)

openpilot/selfdrive/ui/mici/onroad/augmented_road_view.py

@@ -5,6 +5,7 @@ from opendbc.car.structs import car
 from openpilot.cereal.visionipc import VisionStreamType
 from openpilot.selfdrive.ui.ui_state import ui_state, UIStatus
 from openpilot.selfdrive.ui.mici.onroad import SIDE_PANEL_WIDTH
+from openpilot.selfdrive.ui.mici.onroad.accel_boost_indicator import AccelBoostIndicator
 from openpilot.selfdrive.ui.mici.onroad.alert_renderer import AlertRenderer
 from openpilot.selfdrive.ui.mici.onroad.driver_state import DriverStateRenderer
 from openpilot.selfdrive.ui.mici.onroad.hud_renderer import HudRenderer
@@ -181,6 +182,7 @@ class AugmentedRoadView(CameraView):
     self._alert_renderer = AlertRenderer()
     self._driver_state_renderer = DriverStateRenderer()
     self._confidence_ball = ConfidenceBall()
+    self._accel_boost_indicator = AccelBoostIndicator()
     self._offroad_label = UnifiedLabel("start the car to\nuse sunnypilot", 54, FontWeight.DISPLAY,
                                        text_color=rl.Color(255, 255, 255, int(255 * 0.9)),
                                        alignment=TextAlignment.CENTER,
@@ -275,7 +277,10 @@ class AugmentedRoadView(CameraView):
     if show_navigation:
       self._navigation.render(rl.Rectangle(self._content_rect.x + self._content_rect.width, self.rect.y, PANEL_WIDTH, self.rect.height))
     else:
-      self._confidence_ball.render(self.rect)
+      # The boost bar owns the side panel while the extra boost is on; the ball only shows with the feature off
+      self._accel_boost_indicator.render(self.rect)
+      if not self._accel_boost_indicator.panel_in_use:
+        self._confidence_ball.render(self.rect)
 
     self._bookmark_icon.render(self.rect)
 

openpilot/selfdrive/ui/mici/tests/test_accel_boost_indicator.py

@@ -0,0 +1,53 @@
+import unittest
+
+from openpilot.cereal import log
+from openpilot.selfdrive.controls.lib.accel_boost import ACCEL_BOOST_MAX
+from openpilot.selfdrive.ui.mici.onroad.accel_boost_indicator import (get_boost_style, get_boost_fraction, lighten,
+                                                                     AGGRESSIVE_COLOR, RELAXED_COLOR, STANDARD_COLOR)
+from openpilot.sunnypilot.selfdrive.controls.lib.accel_boost_ext import (SCALE_AGGRESSIVE, SCALE_RELAXED, SCALE_STANDARD,
+                                                                        get_accel_boost_max)
+
+
+class TestAccelBoostIndicator(unittest.TestCase):
+  def test_bar_scales_with_following_distance(self):
+    for personality, color, scale in (
+        (log.LongitudinalPersonality.relaxed, RELAXED_COLOR, SCALE_RELAXED),
+        (log.LongitudinalPersonality.standard, STANDARD_COLOR, SCALE_STANDARD),
+        (log.LongitudinalPersonality.aggressive, AGGRESSIVE_COLOR, SCALE_AGGRESSIVE)):
+      bar_color, full_scale = get_boost_style(personality)
+      self.assertEqual(bar_color, color)
+      self.assertAlmostEqual(full_scale, ACCEL_BOOST_MAX * (1.0 + scale))
+
+  def test_bar_fills_at_the_active_profile_cap(self):
+    caps = [get_accel_boost_max(p) for p in (log.LongitudinalPersonality.relaxed,
+                                             log.LongitudinalPersonality.standard,
+                                             log.LongitudinalPersonality.aggressive)]
+    self.assertEqual(caps, sorted(caps))
+
+    for cap in caps:
+      self.assertAlmostEqual(get_boost_fraction(cap, cap), 1.0)
+      self.assertAlmostEqual(get_boost_fraction(0.0, cap), 0.0)
+      self.assertAlmostEqual(get_boost_fraction(cap * 0.5, cap), 0.5)
+
+    # A boost beyond the current cap (e.g. after switching to a shorter profile) still fills the bar
+    self.assertAlmostEqual(get_boost_fraction(caps[2], caps[0]), 1.0)
+    self.assertAlmostEqual(get_boost_fraction(0.0, 0.0), 0.0)
+
+  def test_cap_lighten_keeps_the_profile_hue(self):
+    # An HSV blend towards white sweeps relaxed blue through pink, so the fill lightens in RGB instead
+    relaxed = lighten(RELAXED_COLOR, 0.45)
+    aggressive = lighten(AGGRESSIVE_COLOR, 0.45)
+    self.assertGreater(relaxed.b, relaxed.r)
+    self.assertGreaterEqual(relaxed.b, relaxed.g)
+    self.assertGreater(aggressive.r, aggressive.b)
+    # lighter in RGB means the dimmest channel came up towards white
+    self.assertGreater(relaxed.r, RELAXED_COLOR.r)
+    self.assertGreater(aggressive.g, AGGRESSIVE_COLOR.g)
+
+  def test_wire_personality_picks_the_right_profile(self):
+    # Over the wire personality is a capnp DynamicEnum, which compares equal to the cereal enum but hashes differently
+    msg = log.SelfdriveState.new_message()
+    msg.personality = log.LongitudinalPersonality.aggressive
+    color, full_scale = get_boost_style(msg.personality)
+    self.assertEqual(color, AGGRESSIVE_COLOR)
+    self.assertAlmostEqual(full_scale, get_accel_boost_max(log.LongitudinalPersonality.aggressive))

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

@@ -30,6 +30,11 @@ ACC_NOLONG_DESCRIPTION = tr_noop("This feature can only be used with sunnypilot
 ACC_PCMCRUISE_DISABLED_DESCRIPTION = tr_noop("This feature is not supported on this platform due to vehicle limitations.")
 ONROAD_ONLY_DESCRIPTION = tr_noop("Start the vehicle to check vehicle compatibility.")
 
+ACCEL_BOOST_EXT_DESCRIPTION = tr_noop("Adds extra acceleration on top of the stock gas-override boost when you hold the gas pedal " +
+                                       "while sunnypilot longitudinal control is active. The extra boost follows the Following Distance setting: " +
+                                       "strongest when Aggressive, weakest when Relaxed. The stock boost remains active when this is off.")
+ACCEL_BOOST_EXT_NOLONG_DESCRIPTION = tr_noop("This feature requires sunnypilot longitudinal control to be available.")
+
 
 class CruiseLayout(Widget):
   def __init__(self):
@@ -76,6 +81,11 @@ class CruiseLayout(Widget):
       min_value=1, max_value=3, value_change_step=1,
       inline=True)
 
+    self.accel_boost_toggle = toggle_item_sp(
+      title=tr("Extra Acceleration Boost by Following Distance"),
+      description="",
+      param="FollowDistanceAccelBoost")
+
     self.sla_settings_button = simple_button_item_sp(
       button_text=lambda: tr("Speed Limit"),
       button_width=800,
@@ -86,6 +96,7 @@ class CruiseLayout(Widget):
       self.icbm_toggle,
       self.scc_v_toggle,
       self.scc_m_toggle,
+      self.accel_boost_toggle,
       self.custom_acc_toggle,
       self.custom_acc_short_increment,
       self.custom_acc_long_increment,
@@ -104,6 +115,7 @@ class CruiseLayout(Widget):
     self._scroller.show_event()
     self.icbm_toggle.show_description(True)
     self.custom_acc_toggle.show_description(True)
+    self.accel_boost_toggle.show_description(True)
 
   def _set_current_panel(self, panel: PanelType):
     self._current_panel = panel
@@ -148,10 +160,17 @@ class CruiseLayout(Widget):
         self.scc_v_toggle.action_item.set_enabled(False)
         self.scc_m_toggle.action_item.set_enabled(False)
 
+      self.accel_boost_toggle.action_item.set_enabled(has_long)
+      boost_desc = tr(ACCEL_BOOST_EXT_DESCRIPTION) if has_long else tr(ACCEL_BOOST_EXT_NOLONG_DESCRIPTION)
+      if self.accel_boost_toggle.description != boost_desc:
+        self.accel_boost_toggle.set_description(boost_desc)
+        self.accel_boost_toggle.show_description(True)
+
     else:
       has_icbm = has_long = False
       self.icbm_toggle.action_item.set_enabled(False)
       self.icbm_toggle.set_description(tr(ONROAD_ONLY_DESCRIPTION))
+      self.accel_boost_toggle.action_item.set_enabled(False)
 
     show_custom_acc_desc = False
 

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

@@ -235,13 +235,17 @@ class ModelsLayout(Widget):
     progress = sum(p.progress for p in progresses) / len(progresses)
     ds = custom.ModelManagerSP.DownloadStatus
 
+    if any(p.canceling for p in progresses):
+      return {"name": name, "downloading": True, "progress": progress, "status_text": tr("canceling...")}
     if ds.failed in statuses:
       # close.png is authored black and a tint cannot lift it, hence close2
       return {"name": name, "status_text": tr("download failed"), "text_color": rl.RED, "icon": "icons/close2.png"}
     if ds.verifying in statuses:
       return {"name": name, "downloading": True, "progress": progress, "status_text": tr("verifying")}
     if ds.downloading in statuses:
-      return {"name": name, "downloading": True, "progress": progress}
+      speed = max((p.speed for p in progresses), default=0.0)
+      status_text = f"{speed / 1024 ** 2:.1f} MB/s" if speed > 0 else "--.- MB/s"
+      return {"name": name, "downloading": True, "progress": progress, "status_text": status_text}
     if statuses <= {ds.downloaded, ds.cached}:
       return {"name": name, "text_color": ON_COLOR, "icon": "icons/checkmark.png"}
     # circled_slash is authored grey; tinting it again only darkens it

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

@@ -251,11 +251,13 @@ class ModelsLayoutMici(NavScroller):
       self.current_model_info.info_text.set_text(tr("download failed"))
 
     elif manager.selectedBundle and manager.selectedBundle.status == custom.ModelManagerSP.DownloadStatus.downloading:
-      self.cancel_download_btn.set_visible(True)
+      self.cancel_download_btn.set_visible(ui_state.params.get("ModelManager_DownloadRef") is not None)
       device.set_override_interactive_timeout(5)
       progress = 0.0
       count = 0
       verifying = False
+      canceling = False
+      speed = 0.0
       for model in manager.selectedBundle.models:
         count += 1
         p = model.artifact.downloadProgress
@@ -263,11 +265,14 @@ class ModelsLayoutMici(NavScroller):
                         custom.ModelManagerSP.DownloadStatus.verifying):
           progress += p.progress
           verifying = verifying or p.status == custom.ModelManagerSP.DownloadStatus.verifying
+          canceling = canceling or p.canceling
+          speed = max(speed, p.speed)  # only one file downloads at a time, so the non-zero speed is the live one
         elif p.status in (custom.ModelManagerSP.DownloadStatus.downloaded,
                           custom.ModelManagerSP.DownloadStatus.cached):
           progress += 100.0
 
-      self.current_model_info.current_model_header.set_text(tr("verifying") if verifying else tr("downloading"))
+      header = tr("canceling...") if canceling else tr("verifying") if verifying else tr("downloading")
+      self.current_model_info.current_model_header.set_text(header)
       self.cancel_download_btn.set_text(tr("cancel verification") if verifying else tr("cancel download"))
       self.current_model_info.current_model_header._shimmer = True
       name_text = manager.selectedBundle.internalName.lower()
@@ -276,7 +281,10 @@ class ModelsLayoutMici(NavScroller):
       self.current_model_info.current_model_text.set_text(name_text)
       self.current_model_info.info_header.set_text(tr("progress") + self._download_progress)
       self.current_model_info.info_header._shimmer = True
-      self.current_model_info.info_text.set_text(f"{progress/count:.2f}%")
+      progress_text = f"{progress/count:.2f}%"
+      if not verifying and not canceling:
+        progress_text += f"  |  {speed / 1024 ** 2:.1f} MB/s" if speed > 0 else "  |  --.- MB/s"
+      self.current_model_info.info_text.set_text(progress_text)
 
     elif manager.selectedBundle and manager.selectedBundle.status == custom.ModelManagerSP.DownloadStatus.downloaded:
       self.current_model_info.info_header.set_text(tr("downloaded"))

openpilot/selfdrive/ui/sunnypilot/ui_state.py

@@ -64,6 +64,7 @@ class UIStateSP:
     self.enforce_torque_control: bool = False
     self.custom_torque_params: bool = False
     self.torque_override_enabled: bool = False
+    self.follow_distance_accel_boost: bool = False
     self._sp_initialized: bool = False
 
   def update(self) -> None:
@@ -177,6 +178,7 @@ class UIStateSP:
     self.enforce_torque_control = self.params.get_bool("EnforceTorqueControl")
     self.custom_torque_params = self.params.get_bool("CustomTorqueParams")
     self.torque_override_enabled = self.params.get_bool("TorqueParamsOverrideEnabled")
+    self.follow_distance_accel_boost = self.params.get_bool("FollowDistanceAccelBoost")
     self.torque_override_lat_accel_factor = float(self.params.get("TorqueParamsOverrideLatAccelFactor", return_default=True))
     self.torque_override_friction = float(self.params.get("TorqueParamsOverrideFriction", return_default=True))
     self.true_v_ego_ui = self.params.get_bool("TrueVEgoUI")

openpilot/sunnypilot/modeld_v2/convert_upstream_pkl.py

@@ -7,6 +7,7 @@ See the LICENSE.md file in the root directory for more details.
 """
 import argparse
 import dataclasses
+import inspect
 import itertools
 import mmap
 import re
@@ -45,6 +46,11 @@ def _address(v):
   return _root(v.src[0]), add + start, size
 
 
+def _buffer(u):
+  from tinygrad.uop.ops import Ops
+  return u.buffer if u.op is Ops.BUFFER else getattr(u.arg, "buffer", None)
+
+
 def _patched(buf, topo) -> tuple[bytearray, dict]:
   from tinygrad.uop.ops import Ops
   blob, rows = bytearray(buf.max_numel() * buf.dtype.itemsize), {}
@@ -72,7 +78,7 @@ def _evaluate(u, env):
     table, index = _root(u.src[0].src[0]), _evaluate(u.src[0].src[1], env)
     return struct.unpack_from(u.dtype.fmt, table.arg, index * u.dtype.itemsize)[0] if table.op is Ops.BINARY and index is not None else None
   if u.op in GroupOp.ALU and None not in (values := [_evaluate(x, env) for x in u.src]):
-    return exec_alu(u.op, u.dtype, values, False)
+    return exec_alu(u.op, u.dtype, values, *([False] if "truncate_output" in inspect.signature(exec_alu).parameters else []))
   return None
 
 
@@ -112,7 +118,7 @@ def convert(jit, kwargs: dict, frame: dict, target) -> tuple[dict, memoryview]:
   from tinygrad.uop.ops import Ops
   submit = jit.captured._linear.src[0].without_after
   kernels, topo = submit.arg.aux.kernels, list(jit.captured._linear.toposort(enter_calls=True))
-  allocs = {str(u.tag): u for u in topo if u.op is Ops.ALLOC and u.tag is not None}
+  allocs = {str(name): u for u in topo if u.op is Ops.ALLOC and (name := getattr(u, "tag", None) or u.arg.name) is not None}
   (commands, patched), kernargs = _patched(allocs["cmdbuf_compute_0"], topo), allocs["kernargs_compute_0"]
   argument_words, pokes = _patched(kernargs, topo)[1], _input_pokes(submit, kernargs)
   sh = {name: getattr(amd_gpu, f"reg{name}") + amd_gpu.GC_BASE__INST0_SEG0 - pm4.PACKET3_SET_SH_REG_START
@@ -158,7 +164,7 @@ def convert(jit, kwargs: dict, frame: dict, target) -> tuple[dict, memoryview]:
         args.append({"input": pokes[slot][0]})
       elif slot in argument_words:
         base, at, nbytes = _address(argument_words[slot])
-        args.append({"buffer": buffers.setdefault(base, len(buffers)), "offset": at, "nbytes": nbytes or base.arg.buffer.nbytes, "dtype": u8})
+        args.append({"buffer": buffers.setdefault(base, len(buffers)), "offset": at, "nbytes": nbytes or base.max_numel() * base.dtype.itemsize, "dtype": u8})
     outs, ins = kernel[6]
     calls.append({"kind": "program", "name": re.sub(r"\x1b\[[0-9;]*m", "", kernel[1]), "lib": programs[image_alloc], "target": dataclasses.asdict(target),
                   "signature": [[f"data{i}", i, u8, [a.get("nbytes", 1)]] for i, a in enumerate(args)], "global_size": grid, "local_size": local,
@@ -166,12 +172,13 @@ def convert(jit, kwargs: dict, frame: dict, target) -> tuple[dict, memoryview]:
     needs_init |= {args[i]["buffer"] for i in ins if "buffer" in args[i] and args[i]["buffer"] not in written}
     written |= {args[i]["buffer"] for i in outs if "buffer" in args[i]}
 
+  assert all(_buffer(b) is not None for b, i in buffers.items() if i in needs_init), "a kernel reads a scratch before any kernel writes it"
   names = list(jit.captured.expected_names)
   inputs = [{"slot": slot, "name": names[slot] if slot < len(names) else None, "dtype": repr(u.dtype), "numel": int(u.max_numel()), "device": u.device}
             for slot, u in enumerate(_prepare_jit_inputs((), kwargs)[0])]
   header = {"input_names": names, "calls": calls, "returns": {"kind": "NoneType", "tensors": []}, "inputs": inputs,
-            "buffers": [{"nbytes": b.arg.buffer.nbytes, "device": b.arg.buffer.device, "dtype": u8}
-                        | ({"init": blob.add(b.arg.buffer.ensure_allocated().as_memoryview())} if i in needs_init else {}) for b, i in buffers.items()],
+            "buffers": [{"nbytes": bb.nbytes if (bb := _buffer(b)) else b.max_numel() * b.dtype.itemsize, "device": bb.device if bb else b.device, "dtype": u8}
+                        | ({"init": blob.add(bb.ensure_allocated().as_memoryview())} if i in needs_init else {}) for b, i in buffers.items()],
             "check": {"inputs": [[path, store(array), device] for path, array, device in frame["inputs"]],
                       "outputs": [store(array) for array in frame["outputs"]], "output_container": frame["output_container"]}}
   with sink:

openpilot/sunnypilot/modeld_v2/helpers.py

@@ -250,6 +250,12 @@ def _allocate_buffers(header: dict, blob: memoryview, device_map: dict | None, s
   return buffers
 
 
+def _fields(what, /, **values):  # a tinygrad dataclass built or replaced with the fields it has today: a dropped field is fine, a new required one is not
+  known = {field.name for field in dataclasses.fields(what)}
+  values = {name: value for name, value in values.items() if name in known}
+  return what(**values) if isinstance(what, type) else dataclasses.replace(what, **values)
+
+
 def _program_uop(call: dict, lib: bytes):
   from tinygrad.helpers import Target
   from tinygrad.uop.ops import KernelInfo, Ops, ProgramInfo, UOp
@@ -257,9 +263,9 @@ def _program_uop(call: dict, lib: bytes):
   for name, compact_slot, dtype, shape in call["signature"]:
     parameter = UOp.param(call["globals"][compact_slot], _dtype(dtype), math.prod(shape))
     image = (shape[0], shape[1]) if len(shape) == 3 and shape[2] == 4 else None
-    parameters.append(parameter.replace(arg=dataclasses.replace(parameter.arg, name=name, image=image)))
-  info = ProgramInfo(global_size=tuple(call["global_size"]), local_size=tuple(call["local_size"]), vars=(), globals=tuple(call["globals"]),
-                     outs=tuple(call["outs"]), ins=tuple(call["ins"]), target=Target(**call["target"]))
+    parameters.append(parameter.replace(arg=_fields(parameter.arg, name=name, image=image)))
+  info = _fields(ProgramInfo, global_size=tuple(call["global_size"]), local_size=tuple(call["local_size"]), globals=tuple(call["globals"]),
+                 outs=tuple(call["outs"]), ins=tuple(call["ins"]), target=_fields(Target, **call["target"]))
   return UOp(Ops.PROGRAM, src=(UOp(Ops.SINK, arg=KernelInfo(name=call["name"])), UOp(Ops.LINEAR, src=tuple(parameters)),
                                UOp(Ops.SOURCE, arg=""), UOp(Ops.BINARY, arg=lib)), arg=info)
 

openpilot/sunnypilot/modeld_v2/plain_artifact_compiler.py

@@ -23,7 +23,7 @@ def record_kernel_linear():
   recorded, hcq_compile, compile_linear = [], realize.hcq_compile, jit.compile_linear
 
   def recording_compile_linear(*args, **kwargs):
-    with mock.patch.object(realize, "hcq_compile", lambda linear, *a, **k: (recorded.append(linear), hcq_compile(linear, *a, **k))[1]):
+    with mock.patch.object(realize, "hcq_compile", lambda linear, *a, **k: (linear.src and recorded.append(linear), hcq_compile(linear, *a, **k))[1]):
       return compile_linear(*args, **kwargs)
 
   with mock.patch.object(jit, "compile_linear", recording_compile_linear):
@@ -38,6 +38,18 @@ def capture_frame(jit, kwargs: dict, output_container: str | None = None):
   return {"inputs": inputs, "outputs": [tensor.numpy().copy() for tensor in outputs], "output_container": output_container}, result
 
 
+def kernel_signature(ast, elf) -> list:
+  from tinygrad.dtype import AddrSpace
+  if hasattr(ast, "kernel_params"):
+    if any(p.arg.addrspace is AddrSpace.ALU for p in ast.kernel_params):
+      raise ValueError(f"{elf.name} takes a variable, which plain artifacts don't support")
+    compact = {slot: i for i, slot in enumerate(ast.arg.globals)}
+    return [[p.arg.name, compact[p.arg.slot], repr(p.dtype), [int(x) for x in p._shape]] for p in ast.kernel_params]
+  if not all(isinstance(slot, int) for _, slot, _, _ in elf.signature):
+    raise ValueError("TinyELF.signature lost its slots and this tinygrad has no UOp.kernel_params: update kernel_signature")
+  return [[name, slot, repr(dtype), [int(x) for x in shape]] for name, slot, dtype, shape in elf.signature]
+
+
 def serialize_jit(jit, kernel_linear, check: dict | None = None) -> tuple[dict, memoryview]:
   from tinygrad.uop.ops import Ops
   sink = tempfile.TemporaryFile(dir=".")
@@ -51,6 +63,12 @@ def serialize_jit(jit, kernel_linear, check: dict | None = None) -> tuple[dict,
     if uop.op is Ops.PARAM:
       input_specs.setdefault(uop.arg.slot, {"dtype": repr(uop.dtype), "numel": int(uop.max_numel()), "device": uop.device})
       return {"input": uop.arg.slot}
+    root, offset = uop, 0
+    while root.op in (Ops.AFTER, Ops.BITCAST, Ops.SHRINK):
+      offset, root = offset + (root.src[1].arg * root.src[0].dtype.itemsize if root.op is Ops.SHRINK else 0), root.src[0]
+    if root.op is Ops.ALLOC:
+      base = bases.setdefault(id(root), (len(bases), root, root.dtype))
+      return {"buffer": base[0], "offset": offset, "nbytes": int(uop.max_numel()) * uop.dtype.itemsize, "dtype": repr(uop.dtype)}
     buffer = uop.buffer
     root = buffer._base if buffer._base is not None else buffer
     base = bases.setdefault(id(root), (len(bases), root, uop.base.dtype if buffer._base is None else uop.dtype))
@@ -63,7 +81,7 @@ def serialize_jit(jit, kernel_linear, check: dict | None = None) -> tuple[dict,
       elf, info = ast.to_elf(), ast.arg
       global_size, local_size = info.launch_dims({})
       calls.append({"kind": "program", "name": elf.name, "lib": blob.add(bytes(elf.lib)), "target": dataclasses.asdict(elf.target),
-                    "signature": [[name, slot, repr(dtype), [int(x) for x in shape]] for name, slot, dtype, shape in elf.signature],
+                    "signature": kernel_signature(ast, elf),
                     "global_size": [int(x) for x in global_size], "local_size": [int(x) for x in local_size],
                     "globals": list(info.globals), "outs": list(info.outs), "ins": list(info.ins), "args": arguments})
       outs, ins = info.outs, info.ins
@@ -77,7 +95,9 @@ def serialize_jit(jit, kernel_linear, check: dict | None = None) -> tuple[dict,
 
   ret = jit.captured.ret
   returns = {"kind": type(ret).__name__, "tensors": [describe(t.uop.base) | {"shape": [int(x) for x in t.shape]} for t in flatten(ret)]}
-  buffers = [{"nbytes": base.nbytes, "device": base.device, "dtype": repr(dtype)}
+  from tinygrad.device import Buffer
+  assert not [base for index, base, _ in bases.values() if index in needs_init and not isinstance(base, Buffer)], "a kernel reads a scratch before writing it"
+  buffers = [{"nbytes": base.nbytes if isinstance(base, Buffer) else int(base.max_numel()) * dtype.itemsize, "device": base.device, "dtype": repr(dtype)}
              | ({"init": blob.add(base.as_memoryview())} if index in needs_init else {}) for index, base, dtype in bases.values()]
   names = list(jit.captured.expected_names)
   if check is not None:

openpilot/sunnypilot/modeld_v2/tests/test_convert_upstream_pkl.py

@@ -0,0 +1,121 @@
+"""
+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 os
+import re
+import sys
+import tempfile
+import unittest
+from unittest import mock
+import numpy as np
+
+os.environ.setdefault("CHECK_OOB", "0")
+os.environ.setdefault("GMMU", "0")
+if sys.platform == "darwin" and os.environ.get("DEV", "").startswith("MOCKUSB"):  # the mock's VRAM is a memfd, which macOS lacks: an unlinked file is the same
+  from tinygrad.runtime.autogen import libc
+
+  def _memfd_create(name, flags):
+    fd, path = tempfile.mkstemp()
+    os.unlink(path)
+    return fd
+  libc.memfd_create = _memfd_create
+
+from openpilot.common.test import OpenpilotTestCase
+from openpilot.sunnypilot.modeld_v2 import convert_upstream_pkl
+from openpilot.sunnypilot.modeld_v2.convert_upstream_pkl import convert
+from openpilot.sunnypilot.modeld_v2.helpers import PlainJit, load_model
+from openpilot.sunnypilot.modeld_v2.plain_artifact_compiler import capture_frame
+
+IMG, DESIRE, STATE, OUT = (6, 8, 8), (8,), (4, 16), (1, 32)
+
+
+class TestConvertUpstreamPkl(OpenpilotTestCase):
+  @classmethod
+  def setUpClass(cls):
+    super().setUpClass()
+    if not os.environ.get("TINYGRAD_TESTS"):
+      raise unittest.SkipTest("TINYGRAD_TESTS not set. skipping converter test")
+    from tinygrad import Device, Tensor
+    assert Device.DEFAULT == "AMD" and getattr(Device["AMD"], "is_usb", False), f"{Device.DEFAULT} is not an AMD device behind the USB bridge"
+    assert (Tensor([1, 2, 3]) * 2).tolist() == [2, 4, 6]
+    cls.tmp = tempfile.TemporaryDirectory()
+    cls.rng = np.random.default_rng(0)
+    cls.weights = Tensor(cls.rng.standard_normal((16, 32)).astype(np.float32)).realize()
+    cls.bias = Tensor(cls.rng.standard_normal((1, 32)).astype(np.float32)).realize()
+    cls.input_specs = {"input_imgs": (IMG, "uint8", Device.DEFAULT), "desire": (DESIRE, "float32", Device.DEFAULT),
+                       "features": (STATE, "float32", Device.DEFAULT)}
+    cls.output_specs = {"outputs": (OUT, "float32", Device.DEFAULT), "next_features": (STATE, "float32", Device.DEFAULT)}
+
+  @classmethod
+  def tearDownClass(cls):
+    cls.tmp.cleanup()
+    super().tearDownClass()
+
+  def model(self, input_imgs, desire, features, output_buffers):
+    from tinygrad import Tensor
+    feat = features.mean(axis=0).reshape(1, 16) + input_imgs.float().mean() + desire.sum()
+    Tensor.realize(output_buffers["outputs"].assign((feat @ self.weights + self.bias).relu()),
+                   output_buffers["next_features"].assign(features[1:].cat(feat * 2)))
+
+  def inputs(self, seed: int) -> dict:
+    from examples.openpilot.helpers import allocate_inputs
+    rng = np.random.default_rng(seed)
+
+    def initialize(arrays: dict):
+      for value in arrays.values():
+        value[...] = rng.standard_normal(value.shape) if value.dtype.kind == "f" else rng.integers(0, 256, value.shape)
+    return allocate_inputs(self.input_specs, initialize) | {"output_buffers": allocate_inputs(self.output_specs)}
+
+  def jit(self):
+    from tinygrad import TinyJit
+    run = TinyJit(self.model, prune=True)
+    kwargs = self.inputs(1)
+    run(**kwargs)
+    run(**kwargs)
+    return run
+
+  def assert_matches_eager(self, plain, seed: int):
+    fresh, expected = self.inputs(seed), self.inputs(seed)
+    plain(**fresh)
+    self.model(**expected)
+    for name in self.output_specs:
+      assert np.array_equal(fresh["output_buffers"][name].numpy(), expected["output_buffers"][name].numpy()), name
+
+  def convert(self, jit) -> tuple[dict, memoryview]:
+    from tinygrad import Device
+    kwargs = self.inputs(2)
+    frame, _ = capture_frame(jit, kwargs, "output_buffers")
+    header, blob = convert(jit, kwargs, frame, Device[Device.DEFAULT].renderer.target)
+    kernels = jit.captured._linear.src[0].without_after.arg.aux.kernels
+    assert [call["name"] for call in header["calls"]] == [re.sub(r"\x1b\[[0-9;]*m", "", kernel[1]) for kernel in kernels]
+    assert all(re.fullmatch(r"\w+", call["name"]) for call in header["calls"]), "kernel names: failure point 1"
+    assert [(tuple(call["outs"]), tuple(call["ins"])) for call in header["calls"]] == [tuple(kernel[6]) for kernel in kernels], "outs/ins: failure point 1"
+    bound = {argument["input"] for call in header["calls"] for argument in call["args"] if "input" in argument}
+    assert bound == {spec["slot"] for spec in header["inputs"]}, f"input slots bound by pokes {sorted(bound)}: failure point 4"
+    assert [spec["name"] for spec in header["inputs"]][:len(self.input_specs)] == sorted(self.input_specs)
+    return header, blob
+
+  def test_converted_jit_matches_eager(self):  # the submit decoded into plain calls, replayed against its own frame
+    jit = self.jit()
+    plain = PlainJit(*self.convert(jit))
+    self.assert_matches_eager(plain, 3)
+    self.assert_matches_eager(plain, 4)
+
+  def test_pickle_round_trip_through_main(self):
+    from examples.openpilot.helpers import dump_pickle, load_pickle
+    from tinygrad.engine.realize import lower_and_compile
+    pkl, out = os.path.join(self.tmp.name, "tiny_tinygrad.pkl"), os.path.join(self.tmp.name, "tiny_plain.pkl")
+    dump_pickle({"run": self.jit(), "input_specs": self.input_specs, "output_specs": self.output_specs, "metadata": {"name": "tiny"}}, pkl)
+
+    artifact = load_pickle(pkl, out_of_band=True)
+    artifact["run"].captured._linear = lower_and_compile(artifact["run"].captured._linear)
+    self.assert_matches_eager(PlainJit(*self.convert(artifact["run"])), 5)
+
+    with mock.patch.object(sys, "argv", ["convert_upstream_pkl", pkl, out]):
+      convert_upstream_pkl.main()
+    bundle = load_model(out, cache=False, verify=True)
+    assert bundle["metadata"] == {"name": "tiny"} and bundle["input_specs"] == self.input_specs and bundle["output_specs"] == self.output_specs
+    self.assert_matches_eager(bundle["run"], 6)

openpilot/sunnypilot/modeld_v2/tests/test_plain_artifact.py

@@ -0,0 +1,162 @@
+"""
+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 dataclasses
+import functools
+import inspect
+import os
+import sys
+import tempfile
+from unittest import mock
+import numpy as np
+import unittest
+
+import openpilot.sunnypilot.modeld_v2.helpers as helpers
+from openpilot.common.test import OpenpilotTestCase
+from openpilot.sunnypilot.modeld_v2 import compile_warp
+from openpilot.sunnypilot.modeld_v2.frame_fusion import frame_part, pack_layout
+from openpilot.sunnypilot.modeld_v2.helpers import PlainJit, cache_is_fresh, load_model, read_parts, write_bundle
+from openpilot.sunnypilot.modeld_v2.plain_artifact_compiler import capture_frame, record_kernel_linear, serialize_jit
+
+CAM_W, CAM_H, MODEL_W, MODEL_H = 32, 16, 16, 8
+FRAME = f"{CAM_W},{CAM_H},{CAM_W},{CAM_H},{CAM_H // 2},{CAM_W * CAM_H * 3 // 2}"
+FRAME_SIZE = CAM_W * CAM_H * 3 // 2
+HOST = {"desire": (8,), "traffic_convention": (2,)}
+STATE, OUT = (4, 16), (1, 32)
+
+
+def compile_jit(fn, inputs: dict, output_container: str | None = None) -> tuple[dict, memoryview]:
+  from tinygrad import TinyJit
+  run = TinyJit(fn, prune=True)
+  with record_kernel_linear() as recorded:
+    run(**inputs)
+    run(**inputs)
+    check, _ = capture_frame(run, inputs, output_container)
+  assert len(recorded) == 1, f"expected one captured kernel list, got {len(recorded)}"
+  return serialize_jit(run, recorded[0], check)
+
+
+class TestPlainArtifact(OpenpilotTestCase):
+  @classmethod
+  def setUpClass(cls):
+    super().setUpClass()
+    if not os.environ.get("TINYGRAD_TESTS"):
+      raise unittest.SkipTest("TINYGRAD_TESTS env var not set, skipping artifact test.")
+    from tinygrad import Tensor
+    cls.tmp = tempfile.TemporaryDirectory()
+    cls.rng = np.random.default_rng(0)
+    cls.weights = Tensor(cls.rng.standard_normal((16, 32)).astype(np.float32)).realize()
+    cls.bias = Tensor(cls.rng.standard_normal((1, 32)).astype(np.float32)).realize()
+
+  @classmethod
+  def tearDownClass(cls):
+    cls.tmp.cleanup()
+    super().tearDownClass()
+
+  def model(self, x, h):  # a two input, one weight model: the shape of a policy without the size
+    return ((x @ self.weights + self.bias).relu() + h.mean()).contiguous()
+
+  def tensors(self, seed: int):
+    from tinygrad import Tensor
+    rng = np.random.default_rng(seed)
+    return {"x": Tensor(rng.standard_normal((1, 16)).astype(np.float32)).realize(), "h": Tensor(rng.standard_normal((4, 16)).astype(np.float32)).realize()}
+
+  def artifact(self, name: str = "model") -> str:
+    path = os.path.join(self.tmp.name, f"{name}_tinygrad.pkl")
+    if not os.path.exists(path):
+      write_bundle(path, {"run": compile_jit(self.model, self.tensors(1))}, {"metadata": {"name": name}})
+    return path
+
+  def test_round_trip_matches_jit(self):  # compiler -> bundle -> PlainJit, replay verified, then fresh inputs bit exact with eager tinygrad
+    bundle = load_model(self.artifact(), cache=False, verify=True)
+    assert bundle["metadata"] == {"name": "model"} and isinstance(bundle["run"], PlainJit)
+    fresh = self.tensors(2)
+    assert np.array_equal(bundle["run"](**fresh).numpy(), self.model(**fresh).numpy())
+
+  def test_replay_check_catches_a_changed_kernel(self):
+    parts, extras = read_parts(self.artifact())
+    header, blob = parts["run"]
+    poisoned = dict(header, check=dict(header["check"], outputs=[header["check"]["inputs"][0][1]]))
+    with self.assertRaises(helpers.ArtifactMismatch):
+      PlainJit(poisoned, blob)
+
+  def test_cache_round_trip_holds_no_weights_and_is_rebuilt_when_stale(self):
+    path = self.artifact("cached")
+    expected = load_model(path, cache=False, verify=False)["run"](**self.tensors(3)).numpy()
+    load_model(path)
+    assert cache_is_fresh(path)
+    with open(f"{path}.cache", "rb") as file:
+      cache = file.read()
+    assert self.weights.numpy().tobytes() not in cache and len(cache) < os.path.getsize(path)
+    with mock.patch.object(helpers, "PlainJit", side_effect=AssertionError("a fresh cache must not rebuild")):
+      cached = load_model(path)
+    assert np.array_equal(cached["run"](**self.tensors(3)).numpy(), expected)
+    with mock.patch.object(helpers, "tinygrad_identity", return_value="another tinygrad"):
+      assert not cache_is_fresh(path)
+      assert isinstance(load_model(path)["run"], PlainJit)
+      assert cache_is_fresh(path)
+    assert not cache_is_fresh(path)  # keyed on the tinygrad that wrote it, so the next boot after a bump rebuilds once
+    os.utime(path)
+    with mock.patch.object(helpers, "tinygrad_identity", return_value="another tinygrad"):
+      assert not cache_is_fresh(path)
+
+  def test_fused_with_warp_matches_warp_then_model(self):
+    from tinygrad import Tensor
+    warp_path = os.path.join(self.tmp.name, "warp_tinygrad.pkl")
+    with mock.patch.object(sys, "argv", ["compile_warp", "--frame", FRAME, "--warp-to", f"{MODEL_W}x{MODEL_H}", "--output", warp_path]):
+      compile_warp.main()
+    warp = load_model(warp_path, cache=False)["run"]
+
+    def native(new_img, desire, traffic_convention, state_feat_q, output_buffers):
+      feat = state_feat_q.mean(axis=0).reshape(1, 16) + new_img.float().mean() + desire.sum() + traffic_convention[0]
+      Tensor.realize(output_buffers["outputs"].assign((feat @ self.weights + self.bias).relu()),
+                     output_buffers["next_state_feat_q"].assign(state_feat_q[1:].cat(feat * 2)))
+
+    def model_inputs(new_img):
+      return {"new_img": new_img} | {name: Tensor(np.ones(shape, np.float32) * 0.5).realize() for name, shape in HOST.items()} | \
+             {"state_feat_q": Tensor(self.rng.standard_normal(STATE).astype(np.float32)).realize(),
+              "output_buffers": {"outputs": Tensor.zeros(OUT).contiguous().realize(), "next_state_feat_q": Tensor.zeros(STATE).contiguous().realize()}}
+    frames = Tensor(self.rng.integers(0, 256, (2, FRAME_SIZE), dtype=np.uint8)).realize()
+    tfm = Tensor(np.tile(np.eye(3, dtype=np.float32), (2, 1, 1))).realize()
+    path = os.path.join(self.tmp.name, "native_tinygrad.pkl")
+    part = compile_jit(native, model_inputs(warp(input_frame=frames, M_inv=tfm).realize()), "output_buffers")
+    extras = {"input_specs": {"new_img": ((2, 6, MODEL_H // 2, MODEL_W // 2), "|u1", "CPU"), "state_feat_q": (STATE, "<f4", "CPU")}
+              | {name: (shape, "<f4", "CPU") for name, shape in HOST.items()},
+              "output_specs": {"outputs": (OUT, "<f4", "CPU"), "next_state_feat_q": (STATE, "<f4", "CPU")},
+              "metadata": {"output_shapes": {"outputs": OUT, "next_state_feat_q": STATE}}}
+    write_bundle(path, {"run": part}, extras)
+
+    fused = load_model(path, cache=False, extend=functools.partial(frame_part, warp_path))
+    assert fused["run"].input_names == ["host", "state_feat_q"]
+    offsets, packed = pack_layout(HOST, FRAME_SIZE)
+    host = np.zeros(packed, np.uint8)
+    inputs = model_inputs(None)
+    for name, shape in ({"tfm": (2, 3, 3)} | HOST).items():
+      np.ndarray(shape, np.float32, host, offsets[name])[...] = tfm.numpy() if name == "tfm" else inputs[name].numpy()
+    host[offsets["frames"]:] = frames.numpy().ravel()
+    fused["run"](host=Tensor(host, device="NPY"), state_feat_q=inputs["state_feat_q"], output_buffers=inputs["output_buffers"])
+
+    expected = model_inputs(warp(input_frame=frames, M_inv=tfm).realize()) | {k: inputs[k] for k in ("state_feat_q",)}
+    native(**expected)
+    for name in ("outputs", "next_state_feat_q"):
+      assert np.array_equal(inputs["output_buffers"][name].numpy(), expected["output_buffers"][name].numpy()), name
+
+  def test_tinygrad_api_the_loader_reads(self):
+    import tinygrad.engine.jit as jit
+    from tinygrad.device import Buffer, TinyELF
+    from tinygrad.helpers import Target
+    from tinygrad.uop.ops import ParamArg, ProgramInfo, UOp
+    fields = {cls: {f.name for f in dataclasses.fields(cls)} for cls in (ProgramInfo, ParamArg, Target)}
+    assert fields[ProgramInfo] >= {"global_size", "local_size", "globals", "outs", "ins", "target"}, "ProgramInfo changed: update helpers._program_uop"
+    assert fields[ParamArg] >= {"slot", "dtype", "name", "image"}, "ParamArg changed: update helpers._program_uop"
+    assert fields[Target] >= {"device", "renderer", "arch"}, "Target changed: update the 'target' key in plain_artifact_compiler.serialize_jit"
+    assert "signature" in getattr(TinyELF, "__annotations__", {}) or hasattr(UOp, "kernel_params"), \
+      "kernel signatures moved: update plain_artifact_compiler.serialize_jit"
+    assert callable(getattr(UOp, "param", None)) and callable(getattr(UOp, "from_buffer", None)), "UOp.param/from_buffer: update helpers.PlainJit"
+    assert callable(getattr(UOp, "store_call", None)) and callable(getattr(UOp, "call", None)), "UOp.call/store_call: update helpers.PlainJit"
+    assert callable(getattr(Buffer, "view", None)) and callable(getattr(Buffer, "ensure_allocated", None)), "Buffer.view: update helpers._upload"
+    assert callable(getattr(jit, "compile_linear", None)) and callable(getattr(jit, "_prepare_jit_inputs", None)), "engine.jit: update helpers._Jit"
+    assert "expected_names" in inspect.signature(jit.CapturedJit).parameters, "CapturedJit: update helpers.PlainJit and plain_artifact_compiler.serialize_jit"

openpilot/sunnypilot/models/manager.py

@@ -7,7 +7,10 @@ See the LICENSE.md file in the root directory for more details.
 
 import asyncio
 import os
+import re
+import threading
 import time
+from concurrent.futures import ThreadPoolExecutor
 
 import requests
 from openpilot.common.params import Params
@@ -22,12 +25,101 @@ from openpilot.sunnypilot.models.helpers import (ACTIVE_BUNDLE_KEYS, get_active_
 
 # (connect, read) seconds. read is per-request inactivity, not a total cap
 DOWNLOAD_TIMEOUT = (30, 30)
+# HuggingFace throttles each connection to ~1-2 MB/s but not the connection count; 12 saturates the device link
+MAX_CONCURRENT_PIECES = 12
+PIECE_SIZE = 8 * 1024 * 1024
+PIECE_ATTEMPTS = 3
+PIECE_BACKOFF = 1.0  # seconds, growing linearly: waits 1 s then 2 s between a piece's three attempts
+TRANSIENT_HTTP_STATUS = frozenset({408, 429, 500, 502, 503, 504})
+REPORT_INTERVAL = 0.5  # seconds between progress publications
+# byte ranges count encoded bytes but iter_content yields decoded ones, so ask for an unencoded body
+NO_COMPRESSION = {"Accept-Encoding": "identity"}
+SPEED_SMOOTHING = 0.7  # weight of the previous speed sample in the published speed
+SPEED_FLOOR = 0.05 * 1024 ** 2  # bytes/s; anything slower would only display as 0.0 MB/s, so it reads as no rate
 
 
 class DownloadCancelled(Exception):
   pass
 
 
+def _is_transient(e: BaseException) -> bool:
+  if isinstance(e, requests.HTTPError):
+    return e.response is not None and e.response.status_code in TRANSIENT_HTTP_STATUS
+  return isinstance(e, (requests.ConnectionError, requests.Timeout, requests.exceptions.ChunkedEncodingError))
+
+
+class _Progress:
+  def __init__(self):
+    self._bytes = 0
+    self._lock = threading.Lock()
+
+  def add_bytes(self, n: int) -> None:
+    with self._lock:
+      self._bytes += n
+
+  def snapshot(self) -> int:
+    with self._lock:
+      return self._bytes
+
+
+def _piece_ranges(total: int, piece_size: int) -> list[tuple[int, int]]:
+  return [(start, min(start + piece_size, total)) for start in range(0, total, piece_size)]
+
+
+def _prepare_target(path: str, total: int) -> None:
+  with open(path, "wb") as f:
+    f.truncate(total)
+
+
+def _content_range_total(response: requests.Response) -> int | None:
+  if response.status_code != 206:
+    return None
+  match = re.fullmatch(r"bytes \d+-\d+/(\d+)", response.headers.get("Content-Range", ""))
+  return int(match.group(1)) if match else None
+
+
+def _probe_size(url: str) -> tuple[int, bool]:
+  with requests.get(url, headers={**NO_COMPRESSION, "Range": "bytes=0-0"}, stream=True, timeout=DOWNLOAD_TIMEOUT) as response:
+    response.raise_for_status()
+    total = _content_range_total(response)
+    if total is not None:
+      return total, True
+    return int(response.headers.get("Content-Length", 0)), False
+
+
+def _fetch_piece(url: str, path: str, index: int, start: int, end: int | None, progress: _Progress,
+                 cancel: threading.Event, block_size: int) -> None:
+  headers = {**NO_COMPRESSION, "Range": f"bytes={start}-{end - 1}"} if end is not None else NO_COMPRESSION
+  label = f"{os.path.basename(path)} piece {index}"
+  for attempt in range(PIECE_ATTEMPTS):
+    written = 0
+    try:
+      with requests.get(url, headers=headers, stream=True, timeout=DOWNLOAD_TIMEOUT) as response:
+        response.raise_for_status()
+        if end is not None and response.status_code != 206:
+          raise ValueError(f"server ignored byte range for {label}")
+        with open(path, "r+b") as f:
+          f.seek(start)
+          for block in response.iter_content(chunk_size=block_size):
+            if cancel.is_set():
+              raise DownloadCancelled("Download cancelled")
+            f.write(block)
+            written += len(block)
+            progress.add_bytes(len(block))
+          if end is None:
+            f.truncate()  # unknown length: the body defines the file size
+          if end is not None and written != end - start:
+            raise requests.exceptions.ConnectionError(f"short read: {written} of {end - start} bytes")
+      return
+    except requests.RequestException as e:
+      progress.add_bytes(-written)  # the piece restarts from scratch
+      if not _is_transient(e) or attempt == PIECE_ATTEMPTS - 1:
+        raise
+      cloudlog.warning(f"retrying {label} after {type(e).__name__}: {e}")
+      if cancel.wait(PIECE_BACKOFF * (1 + attempt)):
+        raise DownloadCancelled("Download cancelled") from None
+
+
 class ModelManagerSP:
   """Manages model downloads and status reporting"""
 
@@ -41,7 +133,7 @@ class ModelManagerSP:
     self.source_models: dict[str, list[custom.ModelManagerSP.ModelBundle]] = {}
     self.selected_bundle: custom.ModelManagerSP.ModelBundle = None
     self.active_bundle: custom.ModelManagerSP.ModelBundle = get_active_bundle(self.params, chestnut=self.chestnut_present)
-    self._chunk_size = 128 * 1000  # 128 KB chunks
+    self._block_size = 128 * 1000  # 128 KB network read blocks
     self._download_start_times: dict[str, float] = {}  # Track start time per model
     self._download_ref: bytes | str | None = None
 
@@ -56,7 +148,6 @@ class ModelManagerSP:
     self._download_ref = None
 
   def _sync_artifact_progress(self, source_artifact) -> None:
-    """Mirror download progress to all artifacts sharing the same filename in the selected bundle."""
     if not self.selected_bundle:
       return
     for model in self.selected_bundle.models:
@@ -65,9 +156,9 @@ class ModelManagerSP:
         artifact.downloadProgress.status = source_artifact.downloadProgress.status
         artifact.downloadProgress.progress = source_artifact.downloadProgress.progress
         artifact.downloadProgress.eta = source_artifact.downloadProgress.eta
+        artifact.downloadProgress.speed = source_artifact.downloadProgress.speed
 
   def _calculate_eta(self, filename: str, progress: float) -> int:
-    """Calculate ETA based on elapsed time and current progress"""
     if filename not in self._download_start_times or progress <= 0:
       return 60  # Default ETA for new downloads
 
@@ -75,39 +166,74 @@ class ModelManagerSP:
     if elapsed_time <= 0:
       return 60
 
-    # If we're at X% after Y seconds, we can estimate total time as (Y / X) * 100
     total_estimated_time = (elapsed_time / progress) * 100
     eta = total_estimated_time - elapsed_time
-
     return max(1, int(eta))  # Return at least 1 second if download is ongoing
 
-  async def _download_file(self, url: str, path: str, model) -> None:
-    """Downloads a file with progress tracking"""
-    self._download_start_times[model.fileName] = time.monotonic()
+  def _set_progress(self, artifact, status, progress: float, eta: int = 0, speed: float = 0.0) -> None:
+    artifact.downloadProgress.status = status
+    artifact.downloadProgress.progress = progress
+    artifact.downloadProgress.eta = eta
+    artifact.downloadProgress.speed = speed
+    self._sync_artifact_progress(artifact)
+    self._report_status()
 
-    with requests.get(url, stream=True, timeout=DOWNLOAD_TIMEOUT) as response:  # noqa: ASYNC210
-      response.raise_for_status()
-      total_size = int(response.headers.get("content-length", 0))
-      bytes_downloaded = 0
+  def _publish_progress(self, artifact, done_bytes: int, total: int, speed: float) -> None:
+    # held at 99 until the file passes its hash check
+    progress = min(99.0, done_bytes / total * 100) if total > 0 else 0.0
+    if speed > 0 and total > 0:
+      eta = max(1, int((total - done_bytes) / speed))
+    else:
+      eta = self._calculate_eta(artifact.fileName, progress)
+    self._set_progress(artifact, custom.ModelManagerSP.DownloadStatus.downloading, progress, eta, speed)
 
-      with open(path, 'wb') as f:  # noqa: ASYNC230
-        for chunk in response.iter_content(chunk_size=self._chunk_size):  # type: bytes
-          f.write(chunk)
-          bytes_downloaded += len(chunk)
+  async def _report_until_done(self, tasks: list[asyncio.Future], artifact, progress: _Progress, total: int,
+                               started: tuple[int, float]) -> None:
+    pending = set(tasks)
+    last_bytes, last_time = started
+    speed = 0.0
+    while pending:
+      done, pending = await asyncio.wait(pending, timeout=REPORT_INTERVAL)
+      for task in done:
+        task.result()  # re-raises a worker failure
+      if self._download_interrupted():
+        raise DownloadCancelled("Download cancelled")
+      now = time.monotonic()
+      done_bytes = progress.snapshot()
+      if (dt := now - last_time) > 0:
+        instant = max(0.0, (done_bytes - last_bytes) / dt)  # bytes/s this tick; clamped since retried pieces can lower the byte count
+        speed = instant if speed == 0 else SPEED_SMOOTHING * speed + (1 - SPEED_SMOOTHING) * instant
+        if speed < SPEED_FLOOR:  # a stall decays toward 0 without reaching it, and a near-0 speed overflows the eta
+          speed = 0.0
+      last_time, last_bytes = now, done_bytes
+      self._publish_progress(artifact, done_bytes, total, speed)
 
-          if self._download_interrupted():
-            raise DownloadCancelled("Download cancelled")
+  async def _download_file(self, url: str, path: str, artifact) -> None:
+    self._download_start_times[artifact.fileName] = time.monotonic()
+    loop = asyncio.get_running_loop()
 
-          if total_size > 0:
-            progress = (bytes_downloaded / total_size) * 100
-            model.downloadProgress.status = custom.ModelManagerSP.DownloadStatus.downloading
-            model.downloadProgress.progress = progress
-            model.downloadProgress.eta = self._calculate_eta(model.fileName, progress)
-            self._sync_artifact_progress(model)
-            self._report_status()
+    total, ranged = await loop.run_in_executor(None, _probe_size, url)
+    pieces: list[tuple[int, int | None]] = list(_piece_ranges(total, PIECE_SIZE)) if ranged else [(0, None)]
+    await loop.run_in_executor(None, _prepare_target, path, total)
+    progress = _Progress()
+    cancel = threading.Event()
+    started = progress.snapshot(), time.monotonic()  # before any worker can land bytes
 
-    # Clean up start time after download completes
-    del self._download_start_times[model.fileName]
+    with ThreadPoolExecutor(max_workers=MAX_CONCURRENT_PIECES) as pool:
+      tasks = [loop.run_in_executor(pool, _fetch_piece, url, path, i, start, end, progress, cancel, self._block_size)
+               for i, (start, end) in enumerate(pieces)]
+      try:
+        await self._report_until_done(tasks, artifact, progress, total, started)
+      except BaseException as e:
+        cancel.set()
+        if isinstance(e, DownloadCancelled):
+          artifact.downloadProgress.canceling = True
+          self._set_progress(artifact, custom.ModelManagerSP.DownloadStatus.downloading, artifact.downloadProgress.progress)
+        for task in tasks:
+          task.cancel()  # drops queued pieces; running ones see the event at their next block
+        await asyncio.gather(*tasks, return_exceptions=True)
+        raise
+    del self._download_start_times[artifact.fileName]
 
   async def _process_artifact(self, artifact, destination_path: str) -> None:
     if not artifact.downloadUri.uri:
@@ -119,33 +245,31 @@ class ModelManagerSP:
     expected_hash = artifact.downloadUri.sha256
     filename = artifact.fileName
     full_path = os.path.join(destination_path, filename)
+    status = custom.ModelManagerSP.DownloadStatus
+    artifact.downloadProgress.canceling = False
 
     try:
+      self._set_progress(artifact, status.verifying, 0)
       if await verify_file(full_path, expected_hash):
-        artifact.downloadProgress.status = custom.ModelManagerSP.DownloadStatus.cached
-        artifact.downloadProgress.progress = 100
-        artifact.downloadProgress.eta = 0
-        self._sync_artifact_progress(artifact)
-        self._report_status()
+        self._set_progress(artifact, status.cached, 100)
         return
 
+      self._set_progress(artifact, status.downloading, 0)
       await self._download_file(url, full_path, artifact)
+      self._set_progress(artifact, status.verifying, 99)
       if not await verify_file(full_path, expected_hash):
         raise ValueError(f"Hash validation failed for {filename}")
 
-      artifact.downloadProgress.status = custom.ModelManagerSP.DownloadStatus.downloaded
-      artifact.downloadProgress.progress = 100
-      artifact.downloadProgress.eta = 0
-      self._sync_artifact_progress(artifact)
-      self._report_status()
+      self._set_progress(artifact, status.downloaded, 100)
 
     except DownloadCancelled:
       self._download_start_times.pop(artifact.fileName, None)
-      artifact.downloadProgress.status = custom.ModelManagerSP.DownloadStatus.failed
+      artifact.downloadProgress.status = status.failed
       artifact.downloadProgress.eta = 0
+      artifact.downloadProgress.speed = 0
       self._sync_artifact_progress(artifact)
       if self.selected_bundle:
-        self.selected_bundle.status = custom.ModelManagerSP.DownloadStatus.failed
+        self.selected_bundle.status = status.failed
       self._report_status()
       raise
 
@@ -153,11 +277,12 @@ class ModelManagerSP:
       cloudlog.error(f"Error downloading {filename}: {str(e)}")
       if os.path.isfile(full_path):  # noqa: ASYNC240
         os.remove(full_path)
-      artifact.downloadProgress.status = custom.ModelManagerSP.DownloadStatus.failed
+      artifact.downloadProgress.status = status.failed
       artifact.downloadProgress.eta = 0
+      artifact.downloadProgress.speed = 0
       self._sync_artifact_progress(artifact)
       if self.selected_bundle:
-        self.selected_bundle.status = custom.ModelManagerSP.DownloadStatus.failed
+        self.selected_bundle.status = status.failed
       self._report_status()
       self._download_start_times.pop(artifact.fileName, None)
       raise
@@ -197,6 +322,7 @@ class ModelManagerSP:
           artifact.downloadProgress.status = custom.ModelManagerSP.DownloadStatus.cached
           artifact.downloadProgress.progress = 100
           artifact.downloadProgress.eta = 0
+          artifact.downloadProgress.speed = 0
         else:
           seen_artifacts.add(artifact.fileName)
           await self._process_artifact(artifact, destination_path)
@@ -272,12 +398,7 @@ class ModelManagerSP:
         rk.keep_time()
 
   def clear_model_cache(self) -> None:
-    """
-    Clears the model cache directory of all files except those in the active model bundle.
-    """
-
-    # Get list of files used by both slots' selected bundles (either may become
-    # the truly active bundle depending on hardware availability)
+    """ Clears the model cache directory of all files except those in the active model bundle."""
     active_files = []
     for source in ACTIVE_BUNDLE_KEYS:
       if selected_bundle := get_selected_bundle(self.params, source):
@@ -285,7 +406,6 @@ class ModelManagerSP:
           if model.artifact.fileName:
             active_files.append(model.artifact.fileName)
 
-    # Remove all files except active ones
     model_dir = Paths.model_root()
     try:
       for filename in os.listdir(model_dir):

openpilot/sunnypilot/selfdrive/controls/lib/accel_boost_ext.py

@@ -0,0 +1,72 @@
+"""
+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.
+"""
+from openpilot.cereal import log
+from openpilot.common.params import Params
+from openpilot.common.realtime import DT_MDL
+from openpilot.selfdrive.controls.lib.accel_boost import AccelBoost, ACCEL_BOOST_MAX
+from openpilot.sunnypilot import PARAMS_UPDATE_PERIOD
+
+SCALE_RELAXED = 0.3
+SCALE_STANDARD = 0.5
+SCALE_AGGRESSIVE = 0.7
+
+
+def get_accel_boost_scale(personality) -> float:
+  if personality == log.LongitudinalPersonality.aggressive:
+    return SCALE_AGGRESSIVE
+  if personality == log.LongitudinalPersonality.relaxed:
+    return SCALE_RELAXED
+  return SCALE_STANDARD
+
+
+def get_accel_boost_max(personality, extra_enabled: bool = True) -> float:
+  if not extra_enabled:
+    return ACCEL_BOOST_MAX
+  return ACCEL_BOOST_MAX * (1.0 + get_accel_boost_scale(personality))
+
+
+class AccelBoostExt:
+  def __init__(self, stock: AccelBoost | None = None):
+    self._stock = stock if stock is not None else AccelBoost()
+    self._extra = AccelBoost()
+    self.params = Params()
+    self.frame = -1
+    self.enabled = self.params.get_bool("FollowDistanceAccelBoost")
+
+    self.stock_boost = 0.0
+    self.extra_boost = 0.0
+
+  @property
+  def total_boost(self) -> float:
+    return self._stock.total_boost + self.extra_boost
+
+  def _update_params(self) -> None:
+    if self.frame % int(PARAMS_UPDATE_PERIOD / DT_MDL) == 0:
+      self.enabled = self.params.get_bool("FollowDistanceAccelBoost")
+
+  def update(self, sm, output_a_target_e2e, output_a_target_mpc, a_cruise):
+    self.frame += 1
+    self._update_params()
+
+    if self.enabled and sm['selfdriveState'].enabled:
+      scale = get_accel_boost_scale(sm['selfdriveState'].personality)
+      extra_output = self._extra.update(sm, output_a_target_e2e, output_a_target_mpc, a_cruise)
+      self.extra_boost = (extra_output - output_a_target_e2e) * scale
+    else:
+      self.extra_boost = 0.0
+      self._extra.total_boost = 0.0
+      self._extra.boost_this_override = 0.0
+      self._extra.boost_eligible = False
+
+      output = self._stock.update(sm, output_a_target_e2e, output_a_target_mpc, a_cruise)
+      self.stock_boost = output - output_a_target_e2e
+      return output
+
+    target = output_a_target_e2e + self.extra_boost
+    output = self._stock.update(sm, target, output_a_target_mpc, a_cruise)
+    self.stock_boost = output - target
+    return output

openpilot/sunnypilot/selfdrive/controls/lib/longitudinal_planner.py

@@ -9,6 +9,7 @@ from openpilot.cereal import messaging, custom
 from opendbc.car import structs
 from openpilot.common.constants import CV
 from openpilot.selfdrive.car.cruise import V_CRUISE_MAX
+from openpilot.sunnypilot.selfdrive.controls.lib.accel_boost_ext import AccelBoostExt
 from openpilot.sunnypilot.selfdrive.controls.lib.e2e_alerts_helper import E2EAlertsHelper
 from openpilot.sunnypilot.selfdrive.controls.lib.smart_cruise_control.smart_cruise_control import SmartCruiseControl
 from openpilot.sunnypilot.selfdrive.controls.lib.speed_limit.speed_limit_assist import SpeedLimitAssist
@@ -32,6 +33,16 @@ class LongitudinalPlannerSP:
 
     self.output_v_target = 0.
     self.output_a_target = 0.
+    self._accel_boost: AccelBoostExt | None = None
+
+  @property
+  def accel_boost(self) -> AccelBoostExt:
+    assert self._accel_boost is not None
+    return self._accel_boost
+
+  @accel_boost.setter
+  def accel_boost(self, controller) -> None:
+    self._accel_boost = AccelBoostExt(controller)
 
   def update_targets(self, sm: messaging.SubMaster, v_ego: float, a_ego: float, v_cruise: float) -> tuple[float, float]:
     CS = sm['carState']

openpilot/sunnypilot/selfdrive/controls/lib/tests/test_accel_boost_ext.py

@@ -0,0 +1,237 @@
+from types import SimpleNamespace
+from unittest import mock
+
+from openpilot.cereal import log
+from openpilot.common.realtime import DT_MDL
+from openpilot.common.test import OpenpilotTestCase
+from openpilot.selfdrive.controls.lib.accel_boost import AccelBoost, ACCEL_BOOST_MAX, ACCEL_BOOST_PER_OVERRIDE
+from openpilot.sunnypilot import PARAMS_UPDATE_PERIOD
+from openpilot.sunnypilot.selfdrive.controls.lib.accel_boost_ext import AccelBoostExt, get_accel_boost_max
+from openpilot.sunnypilot.selfdrive.controls.lib.longitudinal_planner import LongitudinalPlannerSP
+
+E2E_ACCEL = 0.5
+PLANNER_ACCEL = 2.0
+STEPS_PER_OVERRIDE = round(ACCEL_BOOST_PER_OVERRIDE / (0.025 * DT_MDL))
+EXPECTED_SCALE = {
+  log.LongitudinalPersonality.relaxed: 0.3,
+  log.LongitudinalPersonality.standard: 0.5,
+  log.LongitudinalPersonality.aggressive: 0.7,
+}
+
+
+class FakeParams:
+  def __init__(self, enabled=True):
+    self.enabled = enabled
+
+  def get_bool(self, key):
+    return self.enabled
+
+
+class FakeSubMaster:
+  def __init__(self, enabled=True, gas_pressed=False, v_ego=15.0,
+               personality=log.LongitudinalPersonality.standard):
+    self._messages = {
+      'selfdriveState': SimpleNamespace(enabled=enabled, personality=personality),
+      'carState': SimpleNamespace(gasPressed=gas_pressed, vEgo=v_ego),
+    }
+
+  def __getitem__(self, key):
+    return self._messages[key]
+
+
+def update(boost, sm, e2e=E2E_ACCEL):
+  return boost.update(sm, e2e, PLANNER_ACCEL, PLANNER_ACCEL)
+
+
+class PlannerStub(LongitudinalPlannerSP):
+  def __init__(self):
+    self._accel_boost = None
+
+
+class TestAccelBoostExt(OpenpilotTestCase):
+  def setUp(self):
+    super().setUp()
+    self.params = FakeParams()
+    patcher = mock.patch("openpilot.sunnypilot.selfdrive.controls.lib.accel_boost_ext.Params", return_value=self.params)
+    patcher.start()
+    self.addCleanup(patcher.stop)
+
+  def _boost_to_max(self, personality):
+    boost = AccelBoostExt()
+    sm = FakeSubMaster(personality=personality)
+    # Eligibility is latched on a frame without gas, then applied on the next override.
+    update(boost, sm)
+    for _ in range(10):
+      sm['carState'].gasPressed = True
+      for _ in range(STEPS_PER_OVERRIDE):
+        update(boost, sm)
+      sm['carState'].gasPressed = False
+      update(boost, sm)
+    return boost, sm
+
+  def _applied_extra(self, boost, sm):
+    update(boost, sm)
+    return boost.extra_boost
+
+  def test_off_matches_stock_boost_exactly(self):
+    self.params.enabled = False
+    sm = FakeSubMaster()
+    stock = AccelBoost()
+    ext = AccelBoostExt()
+
+    stock_out = update(stock, sm)
+    ext_out = update(ext, sm)
+    self.assertAlmostEqual(ext_out, stock_out)
+
+    for _ in range(10):
+      sm['carState'].gasPressed = True
+      for _ in range(STEPS_PER_OVERRIDE):
+        stock_out = update(stock, sm)
+        ext_out = update(ext, sm)
+        self.assertAlmostEqual(ext_out, stock_out)
+      sm['carState'].gasPressed = False
+      stock_out = update(stock, sm)
+      ext_out = update(ext, sm)
+      self.assertAlmostEqual(ext_out, stock_out)
+
+    self.assertAlmostEqual(ext.total_boost, stock.total_boost)
+    self.assertAlmostEqual(ext.stock_boost, stock_out - E2E_ACCEL)
+    self.assertEqual(ext.extra_boost, 0.0)
+    self.assertEqual(ext._extra.total_boost, 0.0)
+
+  def test_no_boost_without_gas(self):
+    ext = AccelBoostExt()
+    sm = FakeSubMaster(gas_pressed=False)
+    out = update(ext, sm)
+    self.assertEqual(ext.total_boost, 0.0)
+    self.assertEqual(ext._extra.total_boost, 0.0)
+    self.assertAlmostEqual(out, E2E_ACCEL)
+
+  def test_boost_requires_e2e_to_be_limiting(self):
+    ext = AccelBoostExt()
+    sm = FakeSubMaster(gas_pressed=False)
+    ext.update(sm, E2E_ACCEL, E2E_ACCEL, E2E_ACCEL)
+    sm['carState'].gasPressed = True
+    for _ in range(10):
+      ext.update(sm, E2E_ACCEL, E2E_ACCEL, E2E_ACCEL)
+    self.assertEqual(ext.total_boost, 0.0)
+    self.assertEqual(ext.stock_boost, 0.0)
+    self.assertEqual(ext.extra_boost, 0.0)
+    self.assertEqual(ext._extra.total_boost, 0.0)
+
+  def test_extra_layer_per_override_cap(self):
+    ext = AccelBoostExt()
+    sm = FakeSubMaster(gas_pressed=False)
+    update(ext, sm)
+    sm['carState'].gasPressed = True
+    for _ in range(1000):
+      update(ext, sm)
+
+    self.assertAlmostEqual(ext._extra.total_boost, ACCEL_BOOST_PER_OVERRIDE)
+    applied = self._applied_extra(ext, sm)
+    expected = ACCEL_BOOST_PER_OVERRIDE * EXPECTED_SCALE[log.LongitudinalPersonality.standard]
+    self.assertAlmostEqual(applied, expected)
+
+  def test_extra_scales_with_following_distance(self):
+    applied = {}
+    for personality in (log.LongitudinalPersonality.relaxed,
+                        log.LongitudinalPersonality.standard,
+                        log.LongitudinalPersonality.aggressive):
+      ext, sm = self._boost_to_max(personality)
+      sm['carState'].gasPressed = True
+      applied[personality] = self._applied_extra(ext, sm)
+
+    for personality, value in applied.items():
+      self.assertAlmostEqual(value, ACCEL_BOOST_MAX * EXPECTED_SCALE[personality])
+
+    self.assertLess(applied[log.LongitudinalPersonality.relaxed], applied[log.LongitudinalPersonality.standard])
+    self.assertLess(applied[log.LongitudinalPersonality.standard], applied[log.LongitudinalPersonality.aggressive])
+
+  def test_capnp_dynamic_enum_personality_scales(self):
+    # Real SubMaster messages expose personality as a capnp DynamicEnum; equality still matches the enum value.
+    msg = log.SelfdriveState.new_message()
+    msg.personality = log.LongitudinalPersonality.aggressive
+    ext, sm = self._boost_to_max(msg.personality)
+    sm['carState'].gasPressed = True
+    applied = self._applied_extra(ext, sm)
+    self.assertAlmostEqual(applied, ACCEL_BOOST_MAX * EXPECTED_SCALE[log.LongitudinalPersonality.aggressive])
+
+  def test_extra_feeds_into_stock_last(self):
+    ext, sm = self._boost_to_max(log.LongitudinalPersonality.standard)
+    sm['carState'].gasPressed = True
+    inputs = []
+    original_update = AccelBoost.update
+
+    def spy(boost, sm_, e2e, mpc, cruise):
+      inputs.append(e2e)
+      return original_update(boost, sm_, e2e, mpc, cruise)
+
+    with mock.patch.object(AccelBoost, "update", spy):
+      out = update(ext, sm)
+
+    # First call is our extra layer on the raw target, last call is stock on the boosted target.
+    self.assertAlmostEqual(inputs[0], E2E_ACCEL)
+    self.assertAlmostEqual(inputs[-1], E2E_ACCEL + ext.extra_boost)
+    self.assertAlmostEqual(out, inputs[-1] + ext.stock_boost)
+
+  def test_extra_is_added_on_top_of_stock_boost(self):
+    ext, sm = self._boost_to_max(log.LongitudinalPersonality.aggressive)
+    sm['carState'].gasPressed = True
+    out = update(ext, sm)
+    extra = out - E2E_ACCEL - ext.stock_boost
+    self.assertAlmostEqual(ext._stock.total_boost, ACCEL_BOOST_MAX)
+    self.assertAlmostEqual(ext.total_boost, ACCEL_BOOST_MAX + ext.extra_boost)
+    self.assertAlmostEqual(ext.stock_boost, ACCEL_BOOST_MAX)
+    self.assertAlmostEqual(ext.extra_boost, ACCEL_BOOST_MAX * EXPECTED_SCALE[log.LongitudinalPersonality.aggressive])
+    self.assertAlmostEqual(extra, ext.extra_boost)
+
+  def test_sp_planner_wraps_assigned_stock_controller(self):
+    planner = PlannerStub()
+    stock = AccelBoost()
+    planner.accel_boost = stock
+
+    self.assertIsInstance(planner.accel_boost, AccelBoostExt)
+    self.assertIs(planner.accel_boost._stock, stock)
+
+  def test_wraps_existing_stock_controller(self):
+    stock = AccelBoost()
+    sm = FakeSubMaster()
+    update(stock, sm)
+    sm['carState'].gasPressed = True
+    update(stock, sm)
+
+    ext = AccelBoostExt(stock)
+    self.assertIs(ext._stock, stock)
+    self.assertAlmostEqual(ext.total_boost, stock.total_boost)
+
+  def test_boost_bar_max_matches_profile_cap(self):
+    for personality, scale in EXPECTED_SCALE.items():
+      self.assertAlmostEqual(get_accel_boost_max(personality), ACCEL_BOOST_MAX * (1.0 + scale))
+      self.assertAlmostEqual(get_accel_boost_max(personality, extra_enabled=False), ACCEL_BOOST_MAX)
+
+  def test_total_boost_is_stock_accumulated_plus_extra_applied(self):
+    ext, sm = self._boost_to_max(log.LongitudinalPersonality.aggressive)
+    sm['carState'].gasPressed = True
+    update(ext, sm)
+    self.assertAlmostEqual(ext.total_boost, ext._stock.total_boost + ext.extra_boost)
+
+  def test_turning_toggle_off_restores_stock_only(self):
+    ext, sm = self._boost_to_max(log.LongitudinalPersonality.aggressive)
+    self.assertGreater(ext._extra.total_boost, 0.0)
+
+    self.params.enabled = False
+    sm['carState'].gasPressed = True
+    # Params are re-read every PARAMS_UPDATE_PERIOD; the extra layer must clear on the next poll.
+    for _ in range(int(PARAMS_UPDATE_PERIOD / DT_MDL) + 1):
+      out = update(ext, sm)
+
+    self.assertEqual(ext._extra.total_boost, 0.0)
+    self.assertEqual(ext.extra_boost, 0.0)
+    self.assertAlmostEqual(out, E2E_ACCEL + ext.stock_boost)
+
+  def test_relaxing_following_distance_applies_immediately(self):
+    ext, sm = self._boost_to_max(log.LongitudinalPersonality.aggressive)
+    sm['selfdriveState'].personality = log.LongitudinalPersonality.relaxed
+    sm['carState'].gasPressed = True
+    applied = self._applied_extra(ext, sm)
+    self.assertAlmostEqual(applied, ACCEL_BOOST_MAX * EXPECTED_SCALE[log.LongitudinalPersonality.relaxed])

openpilot/sunnypilot/sunnylink/settings_ui.json

@@ -620,6 +620,19 @@
                 }
               ]
             },
+            {
+              "key": "FollowDistanceAccelBoost",
+              "widget": "toggle",
+              "title": "Extra Acceleration Boost by Following Distance",
+              "description": "Adds extra acceleration on top of the stock gas-override boost. The extra boost follows the Following Distance setting, strongest when Aggressive and weakest when Relaxed. The stock boost remains active when this is off.",
+              "enablement": [
+                {
+                  "type": "capability",
+                  "field": "has_longitudinal_control",
+                  "equals": true
+                }
+              ]
+            },
             {
               "key": "IntelligentCruiseButtonManagement",
               "widget": "toggle",

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

@@ -30,6 +30,14 @@ sections:
       label: Relaxed
     enablement:
     - $ref: '#/macros/longitudinal'
+  - key: FollowDistanceAccelBoost
+    widget: toggle
+    title: Extra Acceleration Boost by Following Distance
+    description: Adds extra acceleration on top of the stock gas-override boost. The extra boost follows
+      the Following Distance setting, strongest when Aggressive and weakest when Relaxed. The stock boost
+      remains active when this is off.
+    enablement:
+    - $ref: '#/macros/longitudinal'
   - key: IntelligentCruiseButtonManagement
     widget: toggle
     title: Intelligent Cruise Button Management (ICBM) (Alpha)

openpilot/system/ui/sunnypilot/widgets/download_status.py

@@ -57,7 +57,7 @@ class DownloadStatusAction(ItemAction):
     self.icon: str | None = None
     self.icon_color: rl.Color | None = None
     self._font = gui_app.font(FontWeight.NORMAL)
-    # raw progress arrives in steps, one per 128KB chunk the manager publishes
+    # raw progress arrives in steps, one per progress report from the manager
     self._progress = FirstOrderFilter(0.0, 0.5, 1 / gui_app.target_fps)
     # integrated per frame; (t * speed) % span jumps whenever the fill width changes
     self._sweep = 0.0