mirror of
https://github.com/sunnypilot/sunnypilot.git
synced 2026-11-22 18:33:43 +08:00
Compare commits
10 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
| 4664b3e300 | |||
| fcba37990e | |||
| 85423d2b74 | |||
| 2d99b9e47d | |||
| b88039da3f | |||
| f2dd04fec2 | |||
| 0f4c20d430 | |||
| 13097515a6 | |||
| 9489b2f481 | |||
| c270c7835e |
@@ -34,6 +34,11 @@ on:
|
||||
required: false
|
||||
type: string
|
||||
default: 'qcom'
|
||||
on_device:
|
||||
description: 'Compile on the tici / chestnut runner instead of on a hosted runner with tinygrad''s qcom / amd mock'
|
||||
required: false
|
||||
type: boolean
|
||||
default: false
|
||||
hf_repo:
|
||||
description: 'Hugging Face dataset repository (e.g. sunnypilot/sunnypilot_models_v1)'
|
||||
required: false
|
||||
@@ -107,6 +112,11 @@ on:
|
||||
options:
|
||||
- qcom
|
||||
- chestnut
|
||||
on_device:
|
||||
description: 'Compile on the tici / chestnut runner instead of on a hosted runner with tinygrad''s qcom / amd mock'
|
||||
required: false
|
||||
type: boolean
|
||||
default: false
|
||||
hf_repo:
|
||||
description: 'Hugging Face dataset repository'
|
||||
required: false
|
||||
@@ -130,6 +140,7 @@ jobs:
|
||||
is_20hz: ${{ inputs.is_20hz }}
|
||||
artifact_suffix: ${{ inputs.artifact_suffix }}
|
||||
target_hardware: ${{ inputs.target_hardware }}
|
||||
on_device: ${{ inputs.on_device || false }}
|
||||
secrets: inherit
|
||||
|
||||
publish_model:
|
||||
|
||||
@@ -0,0 +1,61 @@
|
||||
name: Chestnut mock build parity
|
||||
description: >-
|
||||
Convert one commaai precompiled chestnut model (LS2) on this runner under tinygrad's amd mock, as a hosted chestnut build does, and require the
|
||||
exact bytes the chestnut runner built (the published artifact). Needs setup-amd-mock, numpy and zstandard; tinygrad_repo checked out.
|
||||
runs:
|
||||
using: composite
|
||||
steps:
|
||||
- name: Key this check by everything its result depends on
|
||||
id: key
|
||||
shell: bash
|
||||
env:
|
||||
SOURCES: ${{ hashFiles('tinygrad_repo/tinygrad/**/*.py', 'tinygrad_repo/test/mockgpu/**', 'openpilot/sunnypilot/modeld_v2/*.py', '.github/workflows/chestnut-build-parity/action.yml') }}
|
||||
run: echo "key=chestnut-build-parity-$SOURCES-$(sha256sum "$LLVM_PATH" | cut -c1-16)-$(python3 -c 'import platform; print(platform.python_version())')" >> "$GITHUB_OUTPUT"
|
||||
|
||||
- name: Passed before with all of it identical?
|
||||
id: passed
|
||||
uses: actions/cache/restore@v4
|
||||
with:
|
||||
path: ~/.chestnut_build_parity.passed
|
||||
key: ${{ steps.key.outputs.key }}
|
||||
|
||||
- name: Rebuild LS2 on the mock and require the chestnut runner's artifact byte for byte
|
||||
if: steps.passed.outputs.cache-hit != 'true'
|
||||
shell: bash
|
||||
env:
|
||||
REF: b92fc4828664f8767bce5e92f1630ed319cbe509 # commaai/openpilot: precompiled big_driving_tinygrad.pkl, pins tinygrad ec91b74b5b
|
||||
PKL_OID: b4dead3ee091d66ab002a6b8e716c26f4f79e3c931e4be5f48e017ba92f6e960
|
||||
PKL_SIZE: "767228907"
|
||||
TG_SHA: ec91b74b5b6b0fc924b72d3f27689679ca2438b9
|
||||
WANT: 680a8d629785f2b1d1a2b0e40d0dfbcd0f7291c21e20c51259f1d768a22ec217 # driving_light_speed_2_november_04_2026_tinygrad.pkl, recompiled46
|
||||
run: |
|
||||
set -euo pipefail
|
||||
work="$RUNNER_TEMP/chestnut_parity" && rm -rf "$work" && mkdir -p "$work"
|
||||
href=$(curl -fsSL --retry 3 -X POST -H "Accept: application/vnd.git-lfs+json" -H "Content-Type: application/vnd.git-lfs+json" \
|
||||
https://huggingface.co/commaai/openpilot-lfs.git/info/lfs/objects/batch \
|
||||
-d "{\"operation\":\"download\",\"transfer\":[\"basic\"],\"objects\":[{\"oid\":\"$PKL_OID\",\"size\":$PKL_SIZE}]}" | jq -r '.objects[0].actions.download.href')
|
||||
curl -fsSL --retry 3 -o "$work/big_driving_tinygrad.pkl" "$href"
|
||||
echo "$PKL_OID $work/big_driving_tinygrad.pkl" | sha256sum -c -
|
||||
tg="$work/tinygrad" && git init -q "$tg" && git -C "$tg" fetch -q --depth 1 https://github.com/tinygrad/tinygrad "$TG_SHA" && git -C "$tg" checkout -q FETCH_HEAD
|
||||
CHECK_OOB=0 GMMU=0 PYTHONPATH="$GITHUB_WORKSPACE/tinygrad_repo" python3 tinygrad_repo/test/mockgpu/usb_server.py \
|
||||
env DEV=USB+AMD PYTHONPATH="$tg:$GITHUB_WORKSPACE" python3 openpilot/sunnypilot/modeld_v2/convert_upstream_pkl.py "$work/big_driving_tinygrad.pkl" "$work/LS2.pkl"
|
||||
got=$(sha256sum "$work/LS2.pkl" | cut -d' ' -f1)
|
||||
if [ "$got" != "$WANT" ]; then
|
||||
echo "::error::the mock's LS2 build ($got) is not the chestnut runner's ($WANT): this runner's LLVM or the mock no longer builds what the chestnut does"
|
||||
exit 1
|
||||
fi
|
||||
echo "LS2 rebuilt on the mock: byte-identical to the chestnut runner's build"
|
||||
touch ~/.chestnut_build_parity.passed
|
||||
|
||||
- name: Remember the pass
|
||||
if: steps.passed.outputs.cache-hit != 'true'
|
||||
uses: actions/cache/save@v4
|
||||
with:
|
||||
path: ~/.chestnut_build_parity.passed
|
||||
key: ${{ steps.key.outputs.key }}
|
||||
|
||||
- name: Already passed
|
||||
if: steps.passed.outputs.cache-hit == 'true'
|
||||
shell: bash
|
||||
run: |
|
||||
echo "LS2 rebuild skipped: it already matched the chestnut runner's build with this exact mock, converter, LLVM and python"
|
||||
@@ -0,0 +1,60 @@
|
||||
name: Set up tinygrad's amd mock
|
||||
description: LLVM 20 and ROCm comgr, as tinygrad_repo/.github/actions/setup-tinygrad installs them for the mock gpu
|
||||
inputs:
|
||||
emu_cache:
|
||||
description: >-
|
||||
Keep tinygrad's cache db (the emulator's compiled kernels and gate results) between runs under this name, e.g. the model's file name.
|
||||
Empty: no cache.
|
||||
default: ''
|
||||
runs:
|
||||
using: composite
|
||||
steps:
|
||||
- name: Install LLVM 20 and ROCm comgr
|
||||
shell: bash
|
||||
run: |
|
||||
. /etc/os-release
|
||||
curl -fsSL https://apt.llvm.org/llvm-snapshot.gpg.key | sudo tee /etc/apt/trusted.gpg.d/apt.llvm.org.asc > /dev/null
|
||||
echo "deb http://apt.llvm.org/$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"
|
||||
llvm=$(ls /usr/lib/llvm-20/lib/libLLVM*.so* /usr/lib/*-linux-gnu/libLLVM-20.so* 2>/dev/null | head -1 || true)
|
||||
[ -n "$llvm" ] || { echo "::error::libLLVM 20 not found"; exit 1; }
|
||||
echo "LLVM_PATH=$llvm" >> "$GITHUB_ENV"
|
||||
|
||||
- name: Cache the chestnut's firmware
|
||||
uses: actions/cache@v4
|
||||
with:
|
||||
path: ~/.cache/tinygrad/downloads/fw
|
||||
key: chestnut-fw-${{ hashFiles('tinygrad_repo/tinygrad/runtime/autogen/am/fw.py') }}
|
||||
|
||||
- name: Fetch the chestnut's firmware (gitlab times out now and then; the mock boots from it)
|
||||
shell: bash
|
||||
run: |
|
||||
for i in 1 2 3 4 5; do
|
||||
PYTHONPATH="$GITHUB_WORKSPACE/tinygrad_repo" python3 -c "
|
||||
from tinygrad.helpers import fetch_fw
|
||||
from tinygrad.runtime.autogen.am import fw
|
||||
for n, h in fw.hashes.items():
|
||||
if n.startswith(('psp_14_0_2_', 'smu_14_0_2.', 'sdma_7_0_0.', 'gc_12_0_0_')): fetch_fw('amdgpu', n, h)" && exit 0
|
||||
sleep $((i * 10))
|
||||
done
|
||||
echo "::error::could not fetch the chestnut's firmware from gitlab"; exit 1
|
||||
|
||||
- name: runner cpu
|
||||
if: inputs.emu_cache != ''
|
||||
id: cpu
|
||||
shell: bash
|
||||
run: echo "cpu=$( (grep -m1 '^model name' /proc/cpuinfo; grep -m1 '^flags' /proc/cpuinfo) | sha256sum | cut -c1-16)" >> "$GITHUB_OUTPUT"
|
||||
|
||||
- name: Keep the emulator's compiled kernels between runs
|
||||
if: inputs.emu_cache != ''
|
||||
uses: actions/cache@v4
|
||||
with:
|
||||
path: ~/.cache/tinygrad/cache.db
|
||||
key: emu-${{ steps.cpu.outputs.cpu }}-${{ hashFiles('tinygrad_repo/tinygrad/**/*.py', 'tinygrad_repo/test/mockgpu/**') }}-${{ inputs.emu_cache }}
|
||||
restore-keys: emu-${{ steps.cpu.outputs.cpu }}-${{ hashFiles('tinygrad_repo/tinygrad/**/*.py', 'tinygrad_repo/test/mockgpu/**') }}-
|
||||
@@ -35,6 +35,11 @@ on:
|
||||
required: false
|
||||
type: string
|
||||
default: 'qcom'
|
||||
on_device:
|
||||
description: 'Compile on the tici / chestnut runner instead of on a hosted runner with tinygrad''s qcom / amd mock'
|
||||
required: false
|
||||
type: boolean
|
||||
default: false
|
||||
workflow_dispatch:
|
||||
inputs:
|
||||
upstream_branch:
|
||||
@@ -59,6 +64,11 @@ on:
|
||||
- qcom
|
||||
- chestnut
|
||||
default: 'qcom'
|
||||
on_device:
|
||||
description: 'Compile on the tici / chestnut runner instead of on a hosted runner with tinygrad''s qcom / amd mock'
|
||||
required: false
|
||||
type: boolean
|
||||
default: false
|
||||
|
||||
|
||||
run-name: Build model [${{ inputs.custom_name || inputs.upstream_branch }}] from ref [${{ inputs.upstream_branch }}]
|
||||
@@ -111,7 +121,12 @@ jobs:
|
||||
grep -qs "^version https://git-lfs" "$f" || continue
|
||||
OID=$(awk -F'sha256:' '/^oid/{print $2}' "$f"); SIZE=$(awk '/^size/{print $2}' "$f")
|
||||
HREF=$(curl -fsSL --retry 3 -X POST -H "Accept: application/vnd.git-lfs+json" -H "Content-Type: application/vnd.git-lfs+json" "$LFS_URL/objects/batch" \
|
||||
-d "{\"operation\":\"download\",\"transfer\":[\"basic\"],\"objects\":[{\"oid\":\"$OID\",\"size\":$SIZE}]}" | jq -r '.objects[0].actions.download.href')
|
||||
-d "{\"operation\":\"download\",\"transfer\":[\"basic\"],\"objects\":[{\"oid\":\"$OID\",\"size\":$SIZE}]}" | jq -r '.objects[0].actions.download.href // empty')
|
||||
if [ -z "$HREF" ]; then
|
||||
HF_PATH=$(curl -fsSL --retry 3 "https://huggingface.co/api/models/commaai/openpilot_driving_models/tree/main?recursive=true" | jq -r --arg oid "$OID" 'map(select(.lfs.oid == $oid))[0].path // empty')
|
||||
[ -n "$HF_PATH" ] || { echo "::error::$f ($OID) is in neither openpilot's LFS nor commaai/openpilot_driving_models"; exit 1; }
|
||||
HREF="https://huggingface.co/commaai/openpilot_driving_models/resolve/main/$HF_PATH"
|
||||
fi
|
||||
aria2c -x 16 -s 16 -k 16M --max-tries=5 --retry-wait=5 --file-allocation=none --summary-interval=30 --allow-overwrite=true \
|
||||
-d "$(dirname "$f")" -o "$(basename "$f")" "$HREF"
|
||||
echo "$OID $f" | sha256sum -c -
|
||||
@@ -119,8 +134,9 @@ jobs:
|
||||
}
|
||||
UPSTREAM_PKL=selfdrive/modeld/models/big_driving_tinygrad.pkl
|
||||
if [ "${{ inputs.target_hardware }}" != "chestnut" ]; then
|
||||
git lfs pull -X "**/selfdrive/modeld/models/big_*.onnx,**/selfdrive/modeld/models/dmonitoring_*.onnx,**/selfdrive/modeld/models/big_*.pkl,**/selfdrive/modeld/models/dmonitoring_*.pkl"
|
||||
git lfs pull -X "**/selfdrive/modeld/models/big_*.onnx,**/selfdrive/modeld/models/dmonitoring_*.onnx,**/selfdrive/modeld/models/big_*.pkl,**/selfdrive/modeld/models/dmonitoring_*.pkl" || true
|
||||
rm -f selfdrive/modeld/models/big_*.onnx selfdrive/modeld/models/dmonitoring_*.onnx selfdrive/modeld/models/big_*.pkl selfdrive/modeld/models/dmonitoring_*.pkl
|
||||
fetch_lfs selfdrive/modeld/models/*.onnx
|
||||
elif compgen -G "selfdrive/modeld/models/big_*.onnx" > /dev/null; then
|
||||
fetch_lfs selfdrive/modeld/models/big_*.onnx selfdrive/modeld/models/big_*.pkl
|
||||
find selfdrive/modeld/models -type f \( -name "*.onnx" -o -name "*.pkl" \) ! -name "big_*.onnx" ! -name "big_*.pkl" -delete
|
||||
@@ -153,18 +169,67 @@ jobs:
|
||||
if-no-files-found: error
|
||||
|
||||
build_model:
|
||||
runs-on: [self-hosted, "${{ inputs.target_hardware == 'chestnut' && 'chestnut' || 'tici' }}"]
|
||||
runs-on: ${{ inputs.on_device && fromJSON(inputs.target_hardware == 'chestnut' && '["self-hosted","chestnut"]' || '["self-hosted","tici"]') || 'ubuntu-24.04' }}
|
||||
needs: get_model
|
||||
env:
|
||||
MODEL_NAME: ${{ inputs.custom_name || inputs.upstream_branch }} (${{ needs.get_model.outputs.model_date }})
|
||||
REF: ${{ inputs.upstream_branch }}
|
||||
MOCK_BUILD: ${{ !inputs.on_device }}
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
with:
|
||||
fetch-depth: 1
|
||||
submodules: recursive
|
||||
|
||||
- name: Set up the hosted mock build
|
||||
if: env.MOCK_BUILD == 'true'
|
||||
uses: actions/setup-python@v5
|
||||
with:
|
||||
python-version: '3.12'
|
||||
|
||||
- name: Install LLVM 20 and ROCm comgr for the amd mock
|
||||
if: env.MOCK_BUILD == 'true' && inputs.target_hardware == 'chestnut'
|
||||
uses: ./.github/workflows/setup-amd-mock
|
||||
with:
|
||||
emu_cache: build
|
||||
|
||||
- name: Install the amd mock build dependencies
|
||||
if: env.MOCK_BUILD == 'true' && inputs.target_hardware == 'chestnut'
|
||||
run: |
|
||||
python3 -m pip install -q numpy zstandard
|
||||
|
||||
- name: Install the qcom mock build dependencies
|
||||
if: env.MOCK_BUILD == 'true' && inputs.target_hardware != 'chestnut'
|
||||
id: qcom_deps
|
||||
run: |
|
||||
sudo apt-get -qq update && sudo apt-get -qq install -y --no-install-recommends qemu-user-static aria2
|
||||
python3 -m pip install -q numpy zstandard tinymesa==25.2.7.2
|
||||
echo "qemu=$(dpkg-query -W -f='${Version}' qemu-user-static)" >> "$GITHUB_OUTPUT"
|
||||
|
||||
- name: Compiler check passed before with all of it identical?
|
||||
if: env.MOCK_BUILD == 'true' && inputs.target_hardware != 'chestnut'
|
||||
id: qcom_compiler
|
||||
uses: actions/cache/restore@v4
|
||||
with:
|
||||
path: ~/.qcom_compiler_parity.passed
|
||||
key: qcom-compiler-parity-${{ steps.qcom_deps.outputs.qemu }}-${{ hashFiles('tinygrad_repo/test/device/qcom/compiler_parity.py', 'tinygrad_repo/test/mockgpu/qcom/a630_compiled.pkl.xz', 'tinygrad_repo/tinygrad/runtime/support/compiler_qcom.py') }}
|
||||
|
||||
- name: Check the off-device qcom compiler builds the a630's bytes
|
||||
if: env.MOCK_BUILD == 'true' && inputs.target_hardware != 'chestnut' && steps.qcom_compiler.outputs.cache-hit != 'true'
|
||||
run: |
|
||||
# every kernel an a630 has compiled must compile to the same bytes here before a model is built here
|
||||
PYTHONPATH="$TINYGRAD_PATH" python3 "$TINYGRAD_PATH/test/device/qcom/compiler_parity.py" check "$TINYGRAD_PATH/test/mockgpu/qcom/a630_compiled.pkl.xz"
|
||||
touch ~/.qcom_compiler_parity.passed
|
||||
|
||||
- name: Remember the compiler check passed
|
||||
if: env.MOCK_BUILD == 'true' && inputs.target_hardware != 'chestnut' && steps.qcom_compiler.outputs.cache-hit != 'true'
|
||||
uses: actions/cache/save@v4
|
||||
with:
|
||||
path: ~/.qcom_compiler_parity.passed
|
||||
key: ${{ steps.qcom_compiler.outputs.cache-primary-key }}
|
||||
|
||||
- name: Set environment variables
|
||||
if: env.MOCK_BUILD != 'true'
|
||||
id: set-env
|
||||
run: |
|
||||
# Set up common environment
|
||||
@@ -177,6 +242,7 @@ jobs:
|
||||
printenv >> $GITHUB_ENV
|
||||
|
||||
- name: Setup build environment
|
||||
if: env.MOCK_BUILD != 'true'
|
||||
run: |
|
||||
mkdir -p "${BUILD_DIR}/"
|
||||
sudo find $BUILD_DIR/ -mindepth 1 -delete
|
||||
@@ -198,21 +264,28 @@ jobs:
|
||||
|
||||
- name: Build Model
|
||||
run: |
|
||||
source /etc/profile
|
||||
export UV_PROJECT_ENVIRONMENT=${HOME}/venv
|
||||
export VIRTUAL_ENV=$UV_PROJECT_ENVIRONMENT
|
||||
source ${UV_PROJECT_ENVIRONMENT}/bin/activate
|
||||
if [ "$MOCK_BUILD" = "true" ]; then
|
||||
TASKSET=""
|
||||
export CHECK_OOB=0 GMMU=0 # as test/mockgpu runs the amd mock
|
||||
else
|
||||
source /etc/profile
|
||||
export UV_PROJECT_ENVIRONMENT=${HOME}/venv
|
||||
export VIRTUAL_ENV=$UV_PROJECT_ENVIRONMENT
|
||||
source ${UV_PROJECT_ENVIRONMENT}/bin/activate
|
||||
TASKSET="taskset -c 7"
|
||||
fi
|
||||
export PYTHONPATH="${PYTHONPATH}:${{ env.TINYGRAD_PATH }}:${{ github.workspace }}"
|
||||
|
||||
COMPILE_MODELD="${{ github.workspace }}/openpilot/sunnypilot/modeld_v2/compile_modeld.py"
|
||||
MODEL_SIZE=$(python3 -c "from openpilot.common.transformations.model import MEDMODEL_INPUT_SIZE as s; print(f'{s[0]}x{s[1]}')")
|
||||
CAMERA_RES=$(python3 -c "from openpilot.common.transformations.camera import _ar_ox_fisheye as a, _os_fisheye as o; print(f'{a.width}x{a.height} {o.width}x{o.height}')")
|
||||
|
||||
TG_FLAGS_QCOM="DEV=QCOM IMAGE=1 FLOAT16=1 NOLOCALS=1 OPENPILOT_HACKS=1"
|
||||
MOCK=$([ "$MOCK_BUILD" = "true" ] && echo MOCK || true)
|
||||
TG_FLAGS_QCOM="DEV=${MOCK:+MOCK+}QCOM IMAGE=1 FLOAT16=1 NOLOCALS=1 OPENPILOT_HACKS=1"
|
||||
if [ "${{ inputs.target_hardware }}" == "chestnut" ]; then
|
||||
echo "CHESTNUT build"
|
||||
export CHESTNUT=1
|
||||
TG_FLAGS="DEBUG=1 DEV=USB+AMD:LLVM FRAME_DEV=CPU FLOAT16=1 GMMU=0 TC_OPT=2 TC_MIN_GLOBALS=32"
|
||||
TG_FLAGS="DEBUG=1 DEV=${MOCK}USB+AMD:LLVM FRAME_DEV=CPU FLOAT16=1 GMMU=0 TC_OPT=2 TC_MIN_GLOBALS=32"
|
||||
OUTPUT_PKL="${{ env.MODELS_DIR }}/big_driving_tinygrad.pkl"
|
||||
else
|
||||
echo "QCOM build"
|
||||
@@ -227,14 +300,16 @@ jobs:
|
||||
echo "Converting commaai's precompiled model with tinygrad $TG_SHA"
|
||||
UPSTREAM_TG="${{ runner.temp }}/upstream_tinygrad"
|
||||
rm -rf "$UPSTREAM_TG" && git init -q "$UPSTREAM_TG" && git -C "$UPSTREAM_TG" fetch -q --depth 1 "$TG_URL" "$TG_SHA" && git -C "$UPSTREAM_TG" checkout -q FETCH_HEAD
|
||||
ON_MOCK=""
|
||||
if [ "$MOCK_BUILD" = "true" ]; then ON_MOCK="env PYTHONPATH=$TINYGRAD_PATH python3 $TINYGRAD_PATH/test/mockgpu/usb_server.py"; fi
|
||||
CONVERTED="${{ runner.temp }}/big_driving_tinygrad_plain.pkl"
|
||||
env DEV=USB+AMD PYTHONPATH="$UPSTREAM_TG:${{ github.workspace }}" taskset -c 7 python3 openpilot/sunnypilot/modeld_v2/convert_upstream_pkl.py \
|
||||
$ON_MOCK env DEV=USB+AMD PYTHONPATH="$UPSTREAM_TG:${{ github.workspace }}" $TASKSET python3 openpilot/sunnypilot/modeld_v2/convert_upstream_pkl.py \
|
||||
"${{ env.MODELS_DIR }}/big_driving_tinygrad.pkl" "$CONVERTED"
|
||||
mv "$CONVERTED" "$OUTPUT_PKL"
|
||||
elif NEW_ARCH_ONNX=$(find "${{ env.MODELS_DIR }}" -maxdepth 1 -name "${{ inputs.target_hardware == 'chestnut' && 'big_' || '' }}*driving*.onnx" -print -quit) &&
|
||||
[ -n "$NEW_ARCH_ONNX" ] && grep -qa new_img "$NEW_ARCH_ONNX"; then # the new architecture: one ONNX taking the warped frames as new_img
|
||||
echo "Compiling new architecture ONNX: $NEW_ARCH_ONNX"
|
||||
env ${TG_FLAGS} taskset -c 7 python3 openpilot/sunnypilot/modeld_v2/compile_modeld_v2.py \
|
||||
env ${TG_FLAGS} $TASKSET python3 openpilot/sunnypilot/modeld_v2/compile_modeld_v2.py \
|
||||
"$NEW_ARCH_ONNX" "$OUTPUT_PKL" --device-input "*" --benchmark-runs 1
|
||||
else
|
||||
echo "Detected onnx architecture. Routing to native compile_modeld.py."
|
||||
@@ -284,7 +359,7 @@ jobs:
|
||||
|
||||
if [ -n "$MODEL_TYPE" ]; then
|
||||
echo "Detected: $MODEL_TYPE -> $OUTPUT_PKL"
|
||||
env ${TG_FLAGS} taskset -c 7 python3 "$COMPILE_MODELD" \
|
||||
env ${TG_FLAGS} $TASKSET python3 "$COMPILE_MODELD" \
|
||||
--model-type $MODEL_TYPE \
|
||||
--model-size $MODEL_SIZE \
|
||||
--camera-resolutions $CAMERA_RES \
|
||||
@@ -293,6 +368,13 @@ jobs:
|
||||
fi
|
||||
fi
|
||||
|
||||
- name: Replay its check frame on the mock and require the result bit for bit
|
||||
if: env.MOCK_BUILD == 'true'
|
||||
env:
|
||||
DEV: ${{ inputs.target_hardware == 'chestnut' && 'MOCKUSB+AMD' || 'MOCK+QCOM' }}
|
||||
PYTHONPATH: ${{ env.TINYGRAD_PATH }}:${{ github.workspace }}
|
||||
run: python3 -m openpilot.sunnypilot.modeld_v2.mock_parity check "${{ env.MODELS_DIR }}/${{ inputs.target_hardware == 'chestnut' && 'big_' || '' }}driving_tinygrad.pkl"
|
||||
|
||||
- name: Prepare Output
|
||||
run: |
|
||||
sudo rm -rf ${{ env.OUTPUT_DIR }}
|
||||
@@ -304,7 +386,7 @@ jobs:
|
||||
--include='/${{ inputs.target_hardware == 'chestnut' && 'big_' || '' }}driving_tinygrad.pkl' \
|
||||
--exclude='*' \
|
||||
--delete-excluded \
|
||||
--chown=comma:comma \
|
||||
$([ "$MOCK_BUILD" = "true" ] || echo --chown=comma:comma) \
|
||||
${{ env.MODELS_DIR }}/ ${{ env.OUTPUT_DIR }}/
|
||||
|
||||
python3 "${{ github.workspace }}/release/ci/model_generator.py" \
|
||||
@@ -333,7 +415,7 @@ jobs:
|
||||
path: ${{ env.OUTPUT_DIR }}/artifact_name.txt
|
||||
|
||||
- name: Re-enable powersave
|
||||
if: always()
|
||||
if: always() && env.MOCK_BUILD != 'true'
|
||||
run: |
|
||||
source ${UV_PROJECT_ENVIRONMENT}/bin/activate
|
||||
PYTHONPATH=$PYTHONPATH:${{ github.workspace }}/ ${{ github.workspace }}/scripts/manage-powersave.py --enable
|
||||
|
||||
@@ -28,18 +28,7 @@ jobs:
|
||||
env:
|
||||
DEV: CPU
|
||||
run: tools/op.sh test -v openpilot/sunnypilot/modeld_v2/tests/test_plain_artifact.py
|
||||
- name: Install LLVM 20 and ROCm comgr for the amd mock, as tinygrad_repo/.github/actions/setup-tinygrad does
|
||||
run: |
|
||||
. /etc/os-release
|
||||
curl -fsSL https://apt.llvm.org/llvm-snapshot.gpg.key | sudo tee /etc/apt/trusted.gpg.d/apt.llvm.org.asc > /dev/null
|
||||
echo "deb http://apt.llvm.org/$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"
|
||||
- uses: ./.github/workflows/setup-amd-mock
|
||||
- name: Convert a pickled USB+AMD jit and replay it under tinygrad's amd mock
|
||||
env:
|
||||
DEV: MOCKUSB+AMD
|
||||
@@ -80,6 +69,8 @@ jobs:
|
||||
runs-on: ubuntu-latest
|
||||
outputs:
|
||||
models: ${{ steps.set-matrix.outputs.models }}
|
||||
chestnut: ${{ steps.set-matrix.outputs.chestnut }}
|
||||
qcom: ${{ steps.set-matrix.outputs.qcom }}
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
- name: Fetch and Parse json
|
||||
@@ -91,16 +82,22 @@ jobs:
|
||||
with open("openpilot/sunnypilot/models/fetcher.py", "r") as f:
|
||||
urls = re.findall(r"MODEL_URL(?:_CHESTNUT)?\s*=\s*[\"'"'"']([^\"'"'"']+)[\"'"'"']", f.read())
|
||||
|
||||
artifacts = []
|
||||
artifacts, chestnut, qcom = [], [], []
|
||||
for url in urls:
|
||||
data = json.loads(urllib.request.urlopen(url).read())
|
||||
for bundle in data.get("bundles", []):
|
||||
for model in bundle.get("models", []):
|
||||
if "artifact" in model:
|
||||
artifacts.append(model["artifact"])
|
||||
if "chestnut" in url:
|
||||
chestnut.append(model["artifact"])
|
||||
elif "tinygrad" in model["artifact"]["file_name"]:
|
||||
qcom.append(model["artifact"])
|
||||
|
||||
with open(os.environ["GITHUB_OUTPUT"], "a") as f:
|
||||
f.write(f"models={json.dumps(artifacts)}\n")
|
||||
f.write(f"chestnut={json.dumps(chestnut)}\n")
|
||||
f.write(f"qcom={json.dumps(qcom)}\n")
|
||||
'
|
||||
|
||||
test-model:
|
||||
@@ -137,3 +134,81 @@ jobs:
|
||||
export PYTHONPATH="$GITHUB_WORKSPACE/tinygrad_repo:$GITHUB_WORKSPACE:$PYTHONPATH"
|
||||
python3 -m pip uninstall -y tinygrad || uv pip uninstall -y tinygrad --system || true
|
||||
python3 -m pytest openpilot/sunnypilot/modeld_v2/tests/test_models.py
|
||||
|
||||
chestnut-mock-parity:
|
||||
name: Mock parity ${{ matrix.artifact.file_name }}
|
||||
needs: generate-matrix
|
||||
runs-on: ubuntu-24.04
|
||||
strategy:
|
||||
fail-fast: false
|
||||
matrix:
|
||||
artifact: ${{ fromJson(needs.generate-matrix.outputs.chestnut) }}
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
with:
|
||||
submodules: true
|
||||
- uses: ./.github/workflows/setup-amd-mock
|
||||
with:
|
||||
emu_cache: ${{ matrix.artifact.file_name }}
|
||||
- run: python3 -m pip install -q numpy
|
||||
- name: Download model
|
||||
env:
|
||||
HF_TOKEN: ${{ secrets.HF_TOKEN }}
|
||||
MODEL_URL: ${{ matrix.artifact.download_uri.url }}
|
||||
MODEL_SHA: ${{ matrix.artifact.download_uri.sha256 }}
|
||||
shell: bash
|
||||
run: |
|
||||
AUTH=()
|
||||
if [ -n "$HF_TOKEN" ]; then AUTH=(-H "Authorization: Bearer $HF_TOKEN"); fi
|
||||
curl --retry 3 --retry-all-errors -s -S -f -L "${AUTH[@]}" -o "$RUNNER_TEMP/model.pkl" "$MODEL_URL"
|
||||
if [ -n "$MODEL_SHA" ]; then echo "$MODEL_SHA $RUNNER_TEMP/model.pkl" | sha256sum -c -; fi
|
||||
- name: Replay its check frame on the amd mock and require the chestnut's result bit for bit
|
||||
env:
|
||||
PYTHONPATH: ${{ github.workspace }}/tinygrad_repo:${{ github.workspace }}
|
||||
run: python3 -m openpilot.sunnypilot.modeld_v2.mock_parity check "$RUNNER_TEMP/model.pkl"
|
||||
|
||||
qcom-mock-parity:
|
||||
name: QCOM mock parity ${{ matrix.artifact.file_name }}
|
||||
needs: generate-matrix
|
||||
runs-on: ubuntu-24.04
|
||||
strategy:
|
||||
fail-fast: false
|
||||
matrix:
|
||||
artifact: ${{ fromJson(needs.generate-matrix.outputs.qcom) }}
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
with:
|
||||
submodules: true
|
||||
- uses: actions/setup-python@v5
|
||||
with:
|
||||
python-version: '3.12'
|
||||
- run: python3 -m pip install -q numpy tinymesa==25.2.7.2
|
||||
- name: Download model
|
||||
env:
|
||||
HF_TOKEN: ${{ secrets.HF_TOKEN }}
|
||||
MODEL_URL: ${{ matrix.artifact.download_uri.url }}
|
||||
MODEL_SHA: ${{ matrix.artifact.download_uri.sha256 }}
|
||||
shell: bash
|
||||
run: |
|
||||
AUTH=()
|
||||
if [ -n "$HF_TOKEN" ]; then AUTH=(-H "Authorization: Bearer $HF_TOKEN"); fi
|
||||
curl --retry 3 --retry-all-errors -s -S -f -L "${AUTH[@]}" -o "$RUNNER_TEMP/model.pkl" "$MODEL_URL"
|
||||
if [ -n "$MODEL_SHA" ]; then echo "$MODEL_SHA $RUNNER_TEMP/model.pkl" | sha256sum -c -; fi
|
||||
- name: Replay its check frame on the qcom mock and require the comma device's result bit for bit
|
||||
env:
|
||||
DEV: MOCK+QCOM
|
||||
PYTHONPATH: ${{ github.workspace }}/tinygrad_repo:${{ github.workspace }}
|
||||
run: python3 -m openpilot.sunnypilot.modeld_v2.mock_parity check "$RUNNER_TEMP/model.pkl"
|
||||
|
||||
chestnut-mock-build-parity:
|
||||
name: Chestnut build on the amd mock = chestnut runner build
|
||||
runs-on: ubuntu-24.04
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
with:
|
||||
submodules: true
|
||||
- uses: ./.github/workflows/setup-amd-mock
|
||||
with:
|
||||
emu_cache: chestnut-build-parity
|
||||
- run: python3 -m pip install -q numpy zstandard
|
||||
- uses: ./.github/workflows/chestnut-build-parity
|
||||
|
||||
@@ -4,7 +4,6 @@
|
||||
[submodule "opendbc"]
|
||||
path = opendbc_repo
|
||||
url = https://github.com/sunnypilot/opendbc.git
|
||||
branch = toyotabsmhack
|
||||
[submodule "msgq"]
|
||||
path = msgq_repo
|
||||
url = https://github.com/sunnypilot/msgq.git
|
||||
|
||||
+1
-1
Submodule opendbc_repo updated: cd009688b0...48eb707e1a
@@ -245,7 +245,6 @@ inline static std::unordered_map<std::string, ParamKeyAttributes> keys = {
|
||||
{"SubaruStopAndGoManualParkingBrake", {PERSISTENT | BACKUP, BOOL, "0"}},
|
||||
{"TeslaCoopSteering", {PERSISTENT | BACKUP, BOOL, "0"}},
|
||||
{"TeslaMadsScreenButton", {PERSISTENT | BACKUP, INT, "0"}},
|
||||
{"ToyotaEnhancedBsm", {PERSISTENT | BACKUP, BOOL, "0"}},
|
||||
{"ToyotaEnforceStockLongitudinal", {PERSISTENT | BACKUP, BOOL, "0"}},
|
||||
{"ToyotaStopAndGoHack", {PERSISTENT | BACKUP, BOOL, "0"}},
|
||||
{"ToyotaTSS2Smooth", {PERSISTENT | BACKUP, BOOL, "0"}},
|
||||
|
||||
@@ -28,6 +28,8 @@ class DesireHelper:
|
||||
self.alc = AutoLaneChangeController(self)
|
||||
self.lane_turn_controller = LaneTurnController(self)
|
||||
self.lane_turn_direction = TurnDirection.none
|
||||
self.turn_frames = 0
|
||||
self.turn_repulse = 98
|
||||
|
||||
@staticmethod
|
||||
def get_lane_change_direction(CS):
|
||||
@@ -95,8 +97,10 @@ class DesireHelper:
|
||||
self.prev_one_blinker = one_blinker and lateral_active
|
||||
|
||||
if self.lane_turn_direction != TurnDirection.none:
|
||||
self.desire = TURN_DESIRES[self.lane_turn_direction]
|
||||
self.turn_frames += 1
|
||||
self.desire = TURN_DESIRES[self.lane_turn_direction] if self.turn_frames % self.turn_repulse else log.Desire.none
|
||||
else:
|
||||
self.turn_frames = 0
|
||||
self.desire = log.Desire.none
|
||||
if self.lane_change_state == LaneChangeState.laneChangeStarting:
|
||||
if self.lane_change_direction == LaneChangeDirection.left:
|
||||
|
||||
@@ -1,3 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:65a08adc31d5c456219687d99b7bf5e44d61dae2d49ea67850e76105c7248cce
|
||||
size 60918562
|
||||
oid sha256:416c99bbd5563b01518be6de91b856986f66ffa03451ea9c451736dcc99896fd
|
||||
size 83976077
|
||||
|
||||
@@ -249,7 +249,11 @@ class ModelsLayout(Widget):
|
||||
return {"name": name, "downloading": True, "progress": progress, "status_text": tr("verifying")}
|
||||
if ds.downloading in statuses:
|
||||
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"
|
||||
speed_text = f"{speed / 1024 ** 2:.1f} MB/s" if speed > 0 else "--.- MB/s"
|
||||
if any(p.resuming for p in progresses):
|
||||
status_text = tr("resuming...") + f" {speed_text}"
|
||||
else:
|
||||
status_text = speed_text
|
||||
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"}
|
||||
|
||||
@@ -11,17 +11,11 @@ from openpilot.system.ui.lib.multilang import tr, tr_noop
|
||||
from openpilot.system.ui.widgets import DialogResult
|
||||
from openpilot.system.ui.widgets.confirm_dialog import ConfirmDialog
|
||||
from openpilot.system.ui.sunnypilot.widgets.list_view import toggle_item_sp
|
||||
from opendbc.car.toyota.values import CAR, ToyotaFlags
|
||||
from opendbc.sunnypilot.car.toyota.values import ToyotaFlagsSP
|
||||
from opendbc.car.toyota.values import ToyotaFlags
|
||||
|
||||
|
||||
ONROAD_ONLY_DESCRIPTION = tr_noop("Start the vehicle to check vehicle compatibility.")
|
||||
SNG_HACK_UNAVAILABLE = tr_noop("sunnypilot Longitudinal Control must be available and enabled for your vehicle to use this feature.")
|
||||
BSM_UNAVAILABLE = tr_noop("Enhanced Blind Spot Monitoring requires a TSS2 Toyota/Lexus without SecOC, " +
|
||||
"or a smartDSU with sunnypilot longitudinal control.")
|
||||
BSM_STOCK_LONG_UNAVAILABLE = tr_noop("Enhanced Blind Spot Monitoring is not available while Enforce Factory Longitudinal Control is enabled.")
|
||||
BSM_REQUIRED = tr_noop("This vehicle does not report blind spot status over the standard CAN signals. " +
|
||||
"Enhanced Blind Spot Monitoring is required for blind spot detection.")
|
||||
PLATFORM_UNAVAILABLE = tr_noop("This feature is currently not available on this platform.")
|
||||
|
||||
DESCRIPTIONS = {
|
||||
@@ -32,10 +26,6 @@ DESCRIPTIONS = {
|
||||
'sunnypilot will allow some Toyota/Lexus cars to auto resume during stop and go traffic. ' +
|
||||
'This feature is only applicable to certain models that are able to use longitudinal control. This is an alpha feature. Use at your own risk.'
|
||||
),
|
||||
'enhanced_bsm': tr_noop(
|
||||
'sunnypilot will poll the blind spot monitor diagnostics directly from the radar. Use this on vehicles whose blind spot monitors ' +
|
||||
'do not report blind spot status over the standard CAN signals. This is an alpha feature. Use at your own risk.'
|
||||
),
|
||||
'tss2_smooth': tr_noop(
|
||||
'Enable smoother longitudinal control for TSS2 vehicles. ' +
|
||||
'Uses a custom speed-dependent integral gain curve for smoother traffic driving.'
|
||||
@@ -63,14 +53,6 @@ class ToyotaSettings(BrandSettings):
|
||||
enabled=lambda: not ui_state.engaged,
|
||||
)
|
||||
|
||||
self.enhanced_bsm = toggle_item_sp(
|
||||
lambda: tr("Enhanced Blind Spot Monitoring (Alpha)"),
|
||||
description=lambda: tr(DESCRIPTIONS["enhanced_bsm"]),
|
||||
initial_state=ui_state.params.get_bool("ToyotaEnhancedBsm"),
|
||||
callback=self._on_enable_enhanced_bsm,
|
||||
enabled=lambda: not ui_state.engaged,
|
||||
)
|
||||
|
||||
self.tss2_smooth = toggle_item_sp(
|
||||
lambda: tr("TSS2 Smooth Longitudinal (Alpha)"),
|
||||
description=lambda: tr(DESCRIPTIONS["tss2_smooth"]),
|
||||
@@ -82,7 +64,6 @@ class ToyotaSettings(BrandSettings):
|
||||
self.items = [
|
||||
self.enforce_stock_longitudinal,
|
||||
self.stop_and_go_hack,
|
||||
self.enhanced_bsm,
|
||||
self.tss2_smooth,
|
||||
]
|
||||
|
||||
@@ -149,25 +130,6 @@ class ToyotaSettings(BrandSettings):
|
||||
ui_state.params.put_bool("ToyotaStopAndGoHack", False)
|
||||
ui_state.params.put_bool("OnroadCycleRequested", True)
|
||||
|
||||
def _on_enable_enhanced_bsm(self, state: bool):
|
||||
if state:
|
||||
def confirm_callback(result: int):
|
||||
if result == DialogResult.CONFIRM:
|
||||
ui_state.params.put_bool("ToyotaEnhancedBsm", True)
|
||||
ui_state.params.put_bool("OnroadCycleRequested", True)
|
||||
else:
|
||||
self.enhanced_bsm.action_item.set_state(False)
|
||||
|
||||
content = (f"<h1>{self.enhanced_bsm.title}</h1><br>" +
|
||||
f"<p>{self.enhanced_bsm.description}</p>")
|
||||
|
||||
dlg = ConfirmDialog(content, tr("Enable"), rich=True, callback=confirm_callback)
|
||||
gui_app.push_widget(dlg)
|
||||
|
||||
else:
|
||||
ui_state.params.put_bool("ToyotaEnhancedBsm", False)
|
||||
ui_state.params.put_bool("OnroadCycleRequested", True)
|
||||
|
||||
def update_settings(self):
|
||||
if ui_state.CP is not None:
|
||||
longitudinal = ui_state.CP.openpilotLongitudinalControl
|
||||
@@ -188,33 +150,6 @@ class ToyotaSettings(BrandSettings):
|
||||
if show_desc:
|
||||
self.stop_and_go_hack.show_description(True)
|
||||
|
||||
# Enhanced BSM needs the radar diagnostic address, which is only in the TX allowlist for
|
||||
# TSS2 cars without SecOC, or for TSS-P cars with a smartDSU. Both need openpilot long.
|
||||
sdsu_bsm_supported = (ui_state.CP_SP is not None and
|
||||
bool(ui_state.CP_SP.flags & ToyotaFlagsSP.SMART_DSU))
|
||||
bsm_supported = (not bool(ui_state.CP.flags & ToyotaFlags.SECOC) and
|
||||
(bool(ui_state.CP.flags & ToyotaFlags.TSS2) or sdsu_bsm_supported))
|
||||
bsm_available = bsm_supported and longitudinal and not enforce_stock
|
||||
self.enhanced_bsm.action_item.set_enabled(bsm_available and not ui_state.engaged)
|
||||
|
||||
bsm_desc = tr(DESCRIPTIONS["enhanced_bsm"])
|
||||
if not bsm_supported:
|
||||
self.enhanced_bsm.action_item.set_state(False)
|
||||
bsm_desc = "<b>" + tr(BSM_UNAVAILABLE) + "</b>\n\n" + bsm_desc
|
||||
elif enforce_stock:
|
||||
self.enhanced_bsm.action_item.set_state(False)
|
||||
bsm_desc = "<b>" + tr(BSM_STOCK_LONG_UNAVAILABLE) + "</b>\n\n" + bsm_desc
|
||||
elif not longitudinal:
|
||||
self.enhanced_bsm.action_item.set_state(False)
|
||||
bsm_desc = "<b>" + tr(SNG_HACK_UNAVAILABLE) + "</b>\n\n" + bsm_desc
|
||||
elif ui_state.CP.carFingerprint == CAR.TOYOTA_PRIUS_TSS2:
|
||||
bsm_desc = "<b>" + tr(BSM_REQUIRED) + "</b>\n\n" + bsm_desc
|
||||
|
||||
if self.enhanced_bsm.description != bsm_desc:
|
||||
self.enhanced_bsm.set_description(bsm_desc)
|
||||
if not bsm_available:
|
||||
self.enhanced_bsm.show_description(True)
|
||||
|
||||
tss2 = bool(ui_state.CP.flags & ToyotaFlags.TSS2)
|
||||
if longitudinal and not enforce_stock and tss2:
|
||||
self.tss2_smooth.action_item.set_enabled(not ui_state.engaged)
|
||||
@@ -238,12 +173,6 @@ class ToyotaSettings(BrandSettings):
|
||||
self.stop_and_go_hack.set_description(new_desc)
|
||||
self.stop_and_go_hack.show_description(True)
|
||||
|
||||
self.enhanced_bsm.action_item.set_enabled(False)
|
||||
bsm_desc = "<b>" + tr(ONROAD_ONLY_DESCRIPTION) + "</b>\n\n" + tr(DESCRIPTIONS["enhanced_bsm"])
|
||||
if self.enhanced_bsm.description != bsm_desc:
|
||||
self.enhanced_bsm.set_description(bsm_desc)
|
||||
self.enhanced_bsm.show_description(True)
|
||||
|
||||
self.tss2_smooth.action_item.set_enabled(False)
|
||||
new_desc = "<b>" + tr(ONROAD_ONLY_DESCRIPTION) + "</b>\n\n" + tr(DESCRIPTIONS["tss2_smooth"])
|
||||
if self.tss2_smooth.description != new_desc:
|
||||
|
||||
@@ -267,8 +267,8 @@ class ModelsLayoutMici(NavScroller):
|
||||
self.current_model_info.info_text.set_text(info_text)
|
||||
|
||||
if manager.selectedBundle and manager.selectedBundle.status == custom.ModelManagerSP.DownloadStatus.failed:
|
||||
self.current_model_info.info_header.set_text(tr("error") + self._download_progress)
|
||||
self.current_model_info.info_text.set_text(tr("download failed"))
|
||||
self.current_model_info.info_header.set_text(tr("error"))
|
||||
self.current_model_info.info_text.set_text(f"{manager.selectedBundle.internalName.lower()} | {tr('download failed')}")
|
||||
|
||||
elif manager.selectedBundle and manager.selectedBundle.status == custom.ModelManagerSP.DownloadStatus.downloading:
|
||||
self.cancel_download_btn.set_visible(ui_state.params.get("ModelManager_DownloadRef") is not None)
|
||||
@@ -277,6 +277,7 @@ class ModelsLayoutMici(NavScroller):
|
||||
count = 0
|
||||
verifying = False
|
||||
canceling = False
|
||||
resuming = False
|
||||
speed = 0.0
|
||||
for model in manager.selectedBundle.models:
|
||||
count += 1
|
||||
@@ -286,12 +287,13 @@ class ModelsLayoutMici(NavScroller):
|
||||
progress += p.progress
|
||||
verifying = verifying or p.status == custom.ModelManagerSP.DownloadStatus.verifying
|
||||
canceling = canceling or p.canceling
|
||||
resuming = resuming or p.resuming
|
||||
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
|
||||
|
||||
header = tr("canceling...") if canceling else tr("verifying") if verifying else tr("downloading")
|
||||
header = tr("canceling...") if canceling else tr("verifying") if verifying else tr("resuming...") if resuming 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
|
||||
|
||||
@@ -8,10 +8,10 @@ import numpy as np
|
||||
|
||||
from openpilot.common.filter_simple import FirstOrderFilter
|
||||
from openpilot.common.realtime import DT_MDL
|
||||
from openpilot.sunnypilot.modeld_v2.constants import ModelConstants
|
||||
from openpilot.sunnypilot.modeld_v2.constants import ModelConstants, Plan
|
||||
|
||||
LANE_WIDTH_DEFAULT = 3.6 # m
|
||||
LANE_WIDTH_CLIP = (2.8, 4.5) # m
|
||||
LANE_WIDTH_CLIP = (2.4, 4.5) # m
|
||||
LOOKAHEAD_TIME = 1.5 # s
|
||||
MIN_LOOKAHEAD = 10.0 # m
|
||||
MIN_SPEED = 5.0 # m/s
|
||||
@@ -19,6 +19,11 @@ LINE_STD = (0.2, 0.6)
|
||||
POINT_STD = 0.1
|
||||
YIELD = (0.2, 0.45)
|
||||
X_IDXS = np.array(ModelConstants.X_IDXS)
|
||||
JUMP = 0.5
|
||||
JUMP_TAU = 0.5
|
||||
JUMP_ACCEPT = 3.0
|
||||
WIDEN = 0.4
|
||||
YAW_RATE = Plan.ORIENTATION_RATE.start + 2 # matched .991 correlation to actual car
|
||||
|
||||
|
||||
class Blendful:
|
||||
@@ -36,7 +41,8 @@ class Blendful:
|
||||
self.l_prob = 0.0
|
||||
self.r_prob = 0.0
|
||||
self.model_curvature = 0.0
|
||||
self.smooth = 0.0 # smooths the correction target below .53 lat accel
|
||||
self.ref = None
|
||||
self.jumped = np.zeros(2)
|
||||
self.curvature = 0.0
|
||||
|
||||
def update(self, model_output: dict[str, np.ndarray], v_ego: float, active: bool, model_curvature: float, enabled: bool = True) -> float:
|
||||
@@ -52,8 +58,8 @@ class Blendful:
|
||||
self.usual_offset.initialized = False
|
||||
self.lane_width.initialized = False
|
||||
self.going_around = False
|
||||
self.ref = None
|
||||
target = 0.0 if fading else self._target(model_output, v_ego, model_curvature)
|
||||
target = self.smooth = self.smooth + (target - self.smooth) * DT_MDL / (DT_MDL + np.interp(abs(model_curvature) * v_ego ** 2, [0.18, 0.53], [0.5, 0.0]))
|
||||
build = 0.5 / max(v_ego, 1.0) ** 2 * DT_MDL # jerk over 1 second
|
||||
release = (0.5 if fading else 2.0) / max(v_ego, 1.0) ** 2 * DT_MDL # lets go fast, but past zero it builds like any other pull
|
||||
k = self.curvature
|
||||
@@ -63,6 +69,10 @@ class Blendful:
|
||||
def _target(self, model_output: dict[str, np.ndarray], v_ego: float, model_curvature: float) -> float:
|
||||
lookahead = max(v_ego * LOOKAHEAD_TIME, MIN_LOOKAHEAD)
|
||||
lines = model_output['lane_lines'][0, :, :, 0]
|
||||
plan = model_output['plan'][0]
|
||||
self._jumps(lines[1:3], v_ego, plan[0, YAW_RATE] if plan.shape[-1] > YAW_RATE else model_curvature * v_ego,
|
||||
np.interp(abs(model_curvature) * v_ego ** 2, [0.18, 0.53], [JUMP_TAU, 0.0]), lookahead)
|
||||
held = bool(np.any((self.jumped > 0) & (self.jumped < JUMP_ACCEPT)))
|
||||
stds = model_output['lane_lines_stds'][0, :, :, 0]
|
||||
|
||||
lone_weight = np.interp(abs(model_curvature) * v_ego ** 2, [0.18, 0.53], [0.5, 1.0]) # 0.5 on straights, 1.0 in curves
|
||||
@@ -83,6 +93,8 @@ class Blendful:
|
||||
lane_trust = min(l_prob, r_prob)
|
||||
else:
|
||||
lane_trust = l_prob + r_prob - l_prob * r_prob
|
||||
if held or (l_prob * r_prob > 0.5 and np.interp(lookahead, X_IDXS, lines[2] - lines[1]) > self.lane_width.x + WIDEN):
|
||||
lane_trust = 0.0
|
||||
if lone_weight > 0.5 and lane_trust < self.line_trust:
|
||||
lane_trust = self.line_trust + (lane_trust - self.line_trust) * DT_MDL / (lone_weight - 0.5 + DT_MDL)
|
||||
self.line_trust = lane_trust
|
||||
@@ -96,7 +108,7 @@ class Blendful:
|
||||
win = (X_IDXS >= 0.5 * lookahead) & (X_IDXS <= 1.5 * lookahead)
|
||||
x = X_IDXS[win]
|
||||
half_width = self.lane_width.x / 2
|
||||
if l_prob * r_prob > 0.5:
|
||||
if l_prob * r_prob > 0.5 and not held:
|
||||
width = np.interp(lookahead, X_IDXS, lines[2]) - np.interp(lookahead, X_IDXS, lines[1])
|
||||
self.lane_width.update(float(np.clip(width, *LANE_WIDTH_CLIP)))
|
||||
half_width = np.clip(lines[2, win] - lines[1, win], *LANE_WIDTH_CLIP) / 2
|
||||
@@ -143,3 +155,14 @@ class Blendful:
|
||||
self.trust = lane_trust if lane_trust < self.trust else self.trust + (lane_trust - self.trust) * DT_MDL / (1.5 + DT_MDL)
|
||||
self.dk = dk
|
||||
return float(self.trust * dk)
|
||||
|
||||
def _jumps(self, raw: np.ndarray, v_ego: float, yaw_rate: float, tau: float, lookahead: float) -> None:
|
||||
if self.ref is None:
|
||||
self.ref, self.jumped = raw.copy(), np.zeros(2)
|
||||
return
|
||||
ref = np.array([np.interp(X_IDXS + v_ego * DT_MDL, X_IDXS, line) for line in self.ref]) - yaw_rate * DT_MDL * X_IDXS
|
||||
off = np.abs([np.interp(lookahead, X_IDXS, d) for d in raw - ref]) > JUMP
|
||||
self.jumped = np.where(off & ~off[::-1], self.jumped + DT_MDL, 0.0)
|
||||
self.ref = ref + (raw - ref) * DT_MDL / (DT_MDL + tau)
|
||||
accept = (self.jumped >= JUMP_ACCEPT) | off.all()
|
||||
self.ref[accept] = raw[accept]
|
||||
|
||||
@@ -371,7 +371,7 @@ def _compile_warp_resolution_worker(cam_w, cam_h, model_w, model_h, benchmark_ru
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
if 'USB' in os.getenv('DEV', '') or os.getenv('CHESTNUT'):
|
||||
if ('USB' in os.getenv('DEV', '') or os.getenv('CHESTNUT')) and not os.getenv('DEV', '').startswith('MOCK'):
|
||||
from openpilot.system.hardware.chestnut.flash import link_up
|
||||
for _ in range(10):
|
||||
if link_up():
|
||||
|
||||
@@ -17,6 +17,7 @@ def main():
|
||||
parser.add_argument("--frame", required=True, help="width,height,stride,y_height,uv_height,buffer_size")
|
||||
parser.add_argument("--warp-to", required=True, help="model input WxH")
|
||||
parser.add_argument("--output", required=True)
|
||||
parser.add_argument("--light", action="store_true")
|
||||
parser.add_argument("--split-frames", action="store_true", help="one input per camera (frame, big_frame), bound to the camera buffers by pointer")
|
||||
args = parser.parse_args()
|
||||
|
||||
@@ -24,18 +25,20 @@ def main():
|
||||
from tinygrad import Device, Tensor, TinyJit
|
||||
frame = parse_frame(args.frame)
|
||||
warp = make_frame_prepare(frame, *parse_size(args.warp_to))
|
||||
n = 1 if args.light else 2
|
||||
cams = list(range(n))
|
||||
rng = np.random.default_rng(42)
|
||||
frames = rng.integers(0, 256, (2, frame.size), dtype=np.uint8)
|
||||
m_inv = Tensor((rng.standard_normal((2, 3, 3)) * 8).astype(np.float32), device=Device.DEFAULT).realize()
|
||||
m_inv = Tensor((rng.standard_normal((n, 3, 3)) * 8).astype(np.float32), device=Device.DEFAULT).realize()
|
||||
if args.split_frames:
|
||||
run = TinyJit(lambda frame, big_frame, M_inv: Tensor.stack(warp(frame, M_inv[0]), warp(big_frame, M_inv[1])), prune=True)
|
||||
inputs = {"frame": Tensor(frames[0], device=Device.DEFAULT).realize(), "big_frame": Tensor(frames[1], device=Device.DEFAULT).realize(), "M_inv": m_inv}
|
||||
specs = {"frame": ((frame.size,), "|u1", Device.DEFAULT), "big_frame": ((frame.size,), "|u1", Device.DEFAULT),
|
||||
"M_inv": ((2, 3, 3), "<f4", Device.DEFAULT)}
|
||||
names = [("frame", "big_frame")[c] for c in cams]
|
||||
run = TinyJit(lambda M_inv, **f: Tensor.stack(*(warp(f[nm], M_inv[i]) for i, nm in enumerate(names))), prune=True)
|
||||
inputs = {nm: Tensor(frames[c], device=Device.DEFAULT).realize() for nm, c in zip(names, cams, strict=True)} | {"M_inv": m_inv}
|
||||
specs = {nm: ((frame.size,), "|u1", Device.DEFAULT) for nm in names} | {"M_inv": ((n, 3, 3), "<f4", Device.DEFAULT)} # noqa: C420
|
||||
else:
|
||||
run = TinyJit(lambda input_frame, M_inv: Tensor.stack(*(warp(input_frame[i], M_inv[i]) for i in range(2))), prune=True)
|
||||
run = TinyJit(lambda input_frame, M_inv: Tensor.stack(*(warp(input_frame[c], M_inv[i]) for i, c in enumerate(cams))), prune=True)
|
||||
inputs = {"input_frame": Tensor(frames, device=Device.DEFAULT).realize(), "M_inv": m_inv}
|
||||
specs = {"input_frame": ((2, frame.size), "|u1", Device.DEFAULT), "M_inv": ((2, 3, 3), "<f4", Device.DEFAULT)}
|
||||
specs = {"input_frame": ((2, frame.size), "|u1", Device.DEFAULT), "M_inv": ((n, 3, 3), "<f4", Device.DEFAULT)}
|
||||
with record_kernel_linear() as recorded:
|
||||
run(**inputs)
|
||||
run(**inputs)
|
||||
|
||||
@@ -10,6 +10,7 @@ import dataclasses
|
||||
import inspect
|
||||
import itertools
|
||||
import mmap
|
||||
import os
|
||||
import re
|
||||
import struct
|
||||
import tempfile
|
||||
@@ -194,7 +195,8 @@ def convert(jit, kwargs: dict, frame: dict, target) -> tuple[dict, memoryview]:
|
||||
base, at, nbytes = _address(argument_words[slot])
|
||||
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),
|
||||
device_target = dataclasses.asdict(dataclasses.replace(target, interface=target.interface.removeprefix("MOCK")))
|
||||
calls.append({"kind": "program", "name": re.sub(r"\x1b\[[0-9;]*m", "", kernel[1]), "lib": programs[image_alloc], "target": device_target,
|
||||
"signature": [[f"data{i}", i, u8, [a.get("nbytes", 1)]] for i, a in enumerate(args)], "global_size": grid, "local_size": local,
|
||||
"globals": list(range(len(args))), "outs": list(outs), "ins": list(ins), "args": args})
|
||||
needs_init |= {args[i]["buffer"] for i in ins if "buffer" in args[i] and args[i]["buffer"] not in written}
|
||||
@@ -235,14 +237,16 @@ def main():
|
||||
frame, _ = capture_frame(artifact["run"], kwargs, "output_buffers")
|
||||
part = convert(artifact["run"], kwargs, frame, Device[Device.DEFAULT].renderer.target)
|
||||
|
||||
plain = PlainJit(*part) # replays the frame, within tolerance
|
||||
replay = {path[0]: Tensor(array, device=device).realize() for path, array, device in frame["inputs"] if len(path) == 1}
|
||||
replay["output_buffers"] = {path[1]: Tensor(array, device=device).realize() for path, array, device in frame["inputs"] if len(path) == 2}
|
||||
flatten(plain(**replay))
|
||||
for index, (got, expected) in enumerate(zip([t.numpy() for t in replay["output_buffers"].values()], frame["outputs"], strict=True)):
|
||||
assert np.array_equal(got, expected), f"output {index} of the plain artifact differs from the pickle"
|
||||
if not os.getenv("MOCKUSB_SOCKET"):
|
||||
plain = PlainJit(*part)
|
||||
replay = {path[0]: Tensor(array, device=device).realize() for path, array, device in frame["inputs"] if len(path) == 1}
|
||||
replay["output_buffers"] = {path[1]: Tensor(array, device=device).realize() for path, array, device in frame["inputs"] if len(path) == 2}
|
||||
flatten(plain(**replay))
|
||||
for index, (got, expected) in enumerate(zip([t.numpy() for t in replay["output_buffers"].values()], frame["outputs"], strict=True)):
|
||||
assert np.array_equal(got, expected), f"output {index} of the plain artifact differs from the pickle"
|
||||
write_bundle(args.output, {"run": part}, {key: artifact[key] for key in ("metadata", "input_specs", "output_specs")})
|
||||
print(f"converted {len(part[0]['calls'])} kernels, bit-exact with the pickle: {args.output}")
|
||||
checked = "left to mock_parity" if os.getenv("MOCKUSB_SOCKET") else "bit-exact with the pickle"
|
||||
print(f"converted {len(part[0]['calls'])} kernels, {checked}: {args.output}")
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
|
||||
@@ -12,8 +12,6 @@ from functools import partial
|
||||
from openpilot.common.basedir import BASEDIR
|
||||
from openpilot.sunnypilot.modeld_v2.helpers import _dtype, read_parts
|
||||
|
||||
SPLIT_FRAMES = ("big_frame", "frame")
|
||||
|
||||
|
||||
def pack_layout(shapes: dict[str, tuple], frame_size: int) -> tuple[dict[str, int], int]:
|
||||
offsets, offset = {}, 0
|
||||
@@ -21,6 +19,13 @@ def pack_layout(shapes: dict[str, tuple], frame_size: int) -> tuple[dict[str, in
|
||||
offsets[name], offset = offset, offset + -(-math.prod(shape) * 4 // 128) * 128
|
||||
return offsets | {"frames": offset}, offset + 2 * frame_size
|
||||
|
||||
EXTRA_WARPS = {"light_img": "light_tfm"}
|
||||
SPLIT_FRAMES = ("big_frame", "frame")
|
||||
|
||||
def host_shapes(input_shapes: dict[str, tuple], states) -> dict[str, tuple]:
|
||||
shapes = {name: shape for name, shape in input_shapes.items() if name not in states and name != "new_img" and name not in EXTRA_WARPS}
|
||||
return shapes | {tfm: (1, 3, 3) for img, tfm in EXTRA_WARPS.items() if img in input_shapes}
|
||||
|
||||
|
||||
class _Blobs: # the model's and the warp's blobs as one address space, for a part whose ranges span both files
|
||||
def __init__(self, *blobs):
|
||||
@@ -32,31 +37,46 @@ class _Blobs: # the model's and the warp's blobs as one address space, for a pa
|
||||
|
||||
|
||||
def fused_with_warp(cam_w: int, cam_h: int, chestnut: bool): # load_model's extend: a native model runs upload, warp and model as one submit
|
||||
return partial(frame_part, f"{BASEDIR}/openpilot/sunnypilot/modeld_v2/models/{'big_' if chestnut else ''}driving_warp_{cam_w}x{cam_h}_tinygrad.pkl")
|
||||
models, big = f"{BASEDIR}/openpilot/sunnypilot/modeld_v2/models", 'big_' if chestnut else ''
|
||||
return partial(frame_part, f"{models}/{big}driving_warp_{cam_w}x{cam_h}_tinygrad.pkl",
|
||||
light_warp_path=f"{models}/{big}driving_lightwarp_{cam_w}x{cam_h}_tinygrad.pkl")
|
||||
|
||||
|
||||
def frame_part(warp_path: str, parts: dict, extras: dict) -> dict:
|
||||
def frame_part(warp_path: str, parts: dict, extras: dict, light_warp_path: str | None = None) -> dict:
|
||||
if "input_specs" not in extras: # a legacy model warps in its own parts
|
||||
return {}
|
||||
(model, model_blob), (warp, warp_blob) = parts["run"], read_parts(warp_path)[0]["run"]
|
||||
states = sorted(name for name in extras["input_specs"] if f"next_{name}" in extras["metadata"]["output_shapes"])
|
||||
host = {name: shape for name, (shape, _, _) in extras["input_specs"].items() if name not in states and name != "new_img"}
|
||||
frame_specs = {s["name"]: s for s in warp["inputs"] if s["name"] in SPLIT_FRAMES}
|
||||
offsets, packed = pack_layout(host, 0 if frame_specs else next(s["numel"] for s in warp["inputs"] if s["name"] == "input_frame") // 2)
|
||||
shift, upload, u8 = len(model_blob), len(model["buffers"]) + len(warp["buffers"]), repr(_dtype("dtypes.uint8"))
|
||||
host = host_shapes({name: shape for name, (shape, _, _) in extras["input_specs"].items()}, states)
|
||||
paths = {"light_img": light_warp_path}
|
||||
extra = [(img, tfm, *read_parts(paths[img])[0]["run"]) for img, tfm in EXTRA_WARPS.items() if img in extras["input_specs"]]
|
||||
split = any(s["name"] in SPLIT_FRAMES for s in warp["inputs"])
|
||||
assert all(any(s["name"] in SPLIT_FRAMES for s in part["inputs"]) == split for _, _, part, _ in extra), "camera and extra warps must share a frame layout"
|
||||
offsets, packed = pack_layout(host, 0 if split else next(s["numel"] for s in warp["inputs"] if s["name"] == "input_frame") // 2)
|
||||
shift = len(model_blob)
|
||||
buf_base, blob_base = [len(model["buffers"]) + len(warp["buffers"])], [len(model_blob) + len(warp_blob)]
|
||||
for _, _, part, blob in extra:
|
||||
buf_base.append(buf_base[-1] + len(part["buffers"])); blob_base.append(blob_base[-1] + len(blob))
|
||||
upload, u8 = buf_base[-1], repr(_dtype("dtypes.uint8"))
|
||||
extra_at = {img: (part, buf_base[i], blob_base[i], tfm) for i, (img, tfm, part, _) in enumerate(extra)}
|
||||
|
||||
def view(name: str, nbytes: int, dtype: str) -> dict:
|
||||
return {"buffer": upload, "offset": offsets[name], "nbytes": nbytes, "dtype": dtype}
|
||||
outputs = sorted(s["slot"] for s in model["inputs"] if s["name"] is None)
|
||||
frame_specs = {s["name"]: s for _, _, part, _ in [(None, None, warp, None), *extra] for s in part["inputs"] if s["name"] in SPLIT_FRAMES}
|
||||
names = sorted(["host", *states, *frame_specs])
|
||||
slots = {s["slot"]: names.index(s["name"]) for s in model["inputs"] if s["name"] in states} | \
|
||||
{slot: len(names) + i for i, slot in enumerate(outputs)}
|
||||
returned = warp["returns"]["tensors"][0]
|
||||
def warped(part: dict, base: int) -> dict:
|
||||
returned = part["returns"]["tensors"][0]
|
||||
return {k: v for k, v in returned.items() if k != "shape"} | {"buffer": returned["buffer"] + base}
|
||||
model_inputs = {s["slot"]: {"input": slots[s["slot"]]} if s["slot"] in slots else
|
||||
{k: v for k, v in returned.items() if k != "shape"} | {"buffer": returned["buffer"] + len(model["buffers"])} if s["name"] == "new_img" else
|
||||
warped(warp, len(model["buffers"])) if s["name"] == "new_img" else
|
||||
warped(extra_at[s["name"]][0], extra_at[s["name"]][1]) if s["name"] in extra_at else
|
||||
view(s["name"], s["numel"] * _dtype(s["dtype"]).itemsize, s["dtype"]) for s in model["inputs"]}
|
||||
warp_inputs = {s["slot"]: {"input": names.index(s["name"])} if s["name"] in frame_specs else
|
||||
view("frames" if s["name"] == "input_frame" else "tfm", s["numel"] * _dtype(s["dtype"]).itemsize, s["dtype"]) for s in warp["inputs"]}
|
||||
def warp_inputs(part: dict, tfm: str) -> dict:
|
||||
return {s["slot"]: {"input": names.index(s["name"])} if s["name"] in frame_specs else
|
||||
view("frames" if s["name"] == "input_frame" else tfm, s["numel"] * _dtype(s["dtype"]).itemsize, s["dtype"]) for s in part["inputs"]}
|
||||
|
||||
def remap(calls: list, inputs: dict, buffers: int, lib: int) -> list:
|
||||
return [call | ({"lib": [call["lib"][0] + lib, call["lib"][1] + lib]} if "lib" in call else {}) |
|
||||
@@ -65,8 +85,11 @@ def frame_part(warp_path: str, parts: dict, extras: dict) -> dict:
|
||||
"inputs": [{"slot": names.index("host"), "name": "host", "dtype": u8, "numel": packed, "device": "NPY"}] +
|
||||
[s | {"slot": slots[s["slot"]]} for s in model["inputs"] if s["slot"] in slots] +
|
||||
[s | {"slot": names.index(name)} for name, s in frame_specs.items()],
|
||||
"buffers": model["buffers"] + [b | ({"init": [b["init"][0] + shift, b["init"][1] + shift]} if "init" in b else {}) for b in warp["buffers"]] +
|
||||
"buffers": model["buffers"] + [b | ({"init": [b["init"][0] + d, b["init"][1] + d]} if "init" in b else {})
|
||||
for part, d in ((warp, shift), *((p, bb) for p, _, bb, _ in extra_at.values())) for b in part["buffers"]] +
|
||||
[{"nbytes": packed, "device": model["inputs"][0]["device"], "dtype": u8}],
|
||||
"calls": [{"kind": "copy", "args": [{"buffer": upload, "offset": 0, "nbytes": packed, "dtype": u8}, {"input": names.index("host")}]}] +
|
||||
remap(warp["calls"], warp_inputs, len(model["buffers"]), shift) + remap(model["calls"], model_inputs, 0, 0)}
|
||||
return {"run": (header, _Blobs(model_blob, warp_blob))} # replaces the model's run: one set of buffers, no separate warp
|
||||
remap(warp["calls"], warp_inputs(warp, "tfm"), len(model["buffers"]), shift) +
|
||||
[c for p, b0, bb, tfm in extra_at.values() for c in remap(p["calls"], warp_inputs(p, tfm), b0, bb)] +
|
||||
remap(model["calls"], model_inputs, 0, 0)}
|
||||
return {"run": (header, _Blobs(model_blob, warp_blob, *(blob for *_, blob in extra)))}
|
||||
|
||||
@@ -0,0 +1,22 @@
|
||||
"""
|
||||
Copyright (c) 2021-, 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 numpy as np
|
||||
|
||||
from openpilot.common.transformations.camera import get_view_frame_from_calib_frame, view_frame_from_device_frame
|
||||
from openpilot.common.transformations.orientation import rot_from_euler
|
||||
|
||||
LIGHT_INPUT_SIZE = (512, 256)
|
||||
light_intrinsics = np.array([
|
||||
[1000.0, 0.0, 256.0],
|
||||
[0.0, 1000.0, 200.0],
|
||||
[0.0, 0.0, 1.0]])
|
||||
calib_from_light = np.linalg.inv((light_intrinsics @ get_view_frame_from_calib_frame(0, 0, 0, 0))[:, :3])
|
||||
|
||||
|
||||
def get_light_warp_matrix(device_from_calib_euler: np.ndarray, intrinsics: np.ndarray) -> np.ndarray:
|
||||
camera_from_calib = intrinsics @ view_frame_from_device_frame @ rot_from_euler(device_from_calib_euler)
|
||||
return (camera_from_calib @ calib_from_light).astype(np.float32)
|
||||
@@ -0,0 +1,153 @@
|
||||
import json
|
||||
import os
|
||||
import shutil
|
||||
import struct
|
||||
import sys
|
||||
import tempfile
|
||||
import time
|
||||
|
||||
os.environ.setdefault("DEV", "MOCKUSB+AMD")
|
||||
QCOM = "QCOM" in os.environ["DEV"]
|
||||
ON_MOCK = os.environ["DEV"].startswith("MOCK")
|
||||
ARCH, HARDWARE = ("a630", "comma 3x/4 (a630)") if QCOM else ("gfx1200", "chestnut")
|
||||
os.environ.setdefault("CHECK_OOB", "0")
|
||||
os.environ.setdefault("GMMU", "0")
|
||||
if sys.platform == "darwin" and os.environ["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
|
||||
|
||||
import numpy as np
|
||||
|
||||
from openpilot.sunnypilot.modeld_v2.helpers import ALIGNMENT, MAGIC, PlainJit, _device, read_parts
|
||||
|
||||
|
||||
class ParityError(RuntimeError):
|
||||
pass
|
||||
|
||||
|
||||
def _emulator():
|
||||
try:
|
||||
if QCOM:
|
||||
from test.mockgpu.qcom import emu
|
||||
else:
|
||||
from test.mockgpu.amd import emu
|
||||
except ImportError as e:
|
||||
raise ParityError(f"tinygrad's {'qcom' if QCOM else 'amd'} mock is not importable: put tinygrad_repo on PYTHONPATH") from e
|
||||
if not hasattr(emu, "hw_unverified"):
|
||||
raise ParityError(f"this tinygrad's emulator has no {ARCH} rounding model, its check frames would not match a {HARDWARE}")
|
||||
return emu
|
||||
|
||||
|
||||
def unverified(header: dict, blob: memoryview) -> dict[str, int]:
|
||||
emu, out = _emulator(), {}
|
||||
for call in header["calls"]:
|
||||
if call["kind"] != "program":
|
||||
continue
|
||||
if (arch := call["target"].get("arch", "")).split(",")[0] != ARCH: # IMAGE builds append ",IMAGE_PITCH_ALIGNMENT=64"
|
||||
out[f"arch={arch}"] = out.get(f"arch={arch}", 0) + 1
|
||||
continue
|
||||
for sig, n in emu.hw_unverified(bytes(blob[slice(*call["lib"])])).items():
|
||||
out[sig] = out.get(sig, 0) + n
|
||||
return out
|
||||
|
||||
|
||||
def _array(blob: memoryview, stored: dict) -> np.ndarray:
|
||||
return np.frombuffer(blob[slice(*stored["data"])], dtype=np.dtype(stored["dtype"])).reshape(stored["shape"]).copy()
|
||||
|
||||
|
||||
def replay(header: dict, blob: memoryview, shared: dict) -> list[np.ndarray]:
|
||||
from tinygrad import Tensor
|
||||
check = header["check"]
|
||||
jit = PlainJit(header, blob, None, verify=False, shared=shared)
|
||||
kwargs: dict = {}
|
||||
for path, stored, device in check["inputs"]:
|
||||
tensor = Tensor(_array(blob, stored), device=_device(device, None)).realize()
|
||||
kwargs[path[0]] = tensor if len(path) == 1 else {**kwargs.get(path[0], {}), path[1]: tensor}
|
||||
result = jit(**kwargs)
|
||||
outputs = kwargs[check["output_container"]].values() if check["output_container"] else result
|
||||
return [t.numpy() for t in (outputs if isinstance(outputs, (list, tuple)) or check["output_container"] else [outputs])]
|
||||
|
||||
|
||||
def _parts_with_offsets(path: str) -> tuple[dict, dict]:
|
||||
parts, _ = read_parts(path)
|
||||
with open(path, "rb") as f:
|
||||
head = f.read(len(MAGIC) + 8)
|
||||
start = len(MAGIC) + 8 + struct.unpack_from("<Q", head, len(MAGIC))[0]
|
||||
f.seek(len(MAGIC) + 8)
|
||||
entries = json.loads(f.read(start - len(MAGIC) - 8))["parts"]
|
||||
base = start + -start % ALIGNMENT
|
||||
offsets = {tuple(e["key"]) if isinstance(e["key"], list) else e["key"]: base + e["blob"][0] for e in entries}
|
||||
return parts, offsets
|
||||
|
||||
|
||||
def _gate(parts: dict) -> None:
|
||||
missing: dict[str, int] = {}
|
||||
for header, blob in parts.values():
|
||||
if "check" not in header:
|
||||
raise ParityError("artifact has no check frame")
|
||||
for sig, n in unverified(header, blob).items():
|
||||
missing[sig] = missing.get(sig, 0) + n
|
||||
if missing:
|
||||
raise ParityError(f"kernels use instructions the emulator is not verified against a {HARDWARE} for: " +
|
||||
", ".join(f"{s} ({n}x)" for s, n in sorted(missing.items(), key=lambda kv: -kv[1])))
|
||||
|
||||
|
||||
def check(path: str) -> None:
|
||||
parts, _ = read_parts(path)
|
||||
if ON_MOCK:
|
||||
_gate(parts)
|
||||
shared: dict = {}
|
||||
for key, (header, blob) in parts.items():
|
||||
got = replay(header, blob, shared)
|
||||
for i, (g, stored) in enumerate(zip(got, header["check"]["outputs"], strict=True)):
|
||||
want = _array(blob, stored)
|
||||
if g.shape != want.shape or not np.array_equal(g.view(np.uint8), want.view(np.uint8)):
|
||||
n = int(np.count_nonzero(g != want)) if g.shape == want.shape else -1
|
||||
where = "mock" if ON_MOCK else "device"
|
||||
raise ParityError(f"part {key} output {i}: the {where}'s check frame differs from the stored one in {n} of {want.size} values")
|
||||
|
||||
|
||||
def record(path: str, out: str) -> None:
|
||||
parts, offsets = _parts_with_offsets(path)
|
||||
_gate(parts)
|
||||
shared, writes = {}, []
|
||||
for key, (header, blob) in parts.items():
|
||||
for g, stored in zip(replay(header, blob, shared), header["check"]["outputs"], strict=True):
|
||||
want = np.dtype(stored["dtype"])
|
||||
if tuple(g.shape) != tuple(stored["shape"]) or g.dtype != want:
|
||||
raise ParityError(f"part {key}: replayed output {g.dtype}{g.shape} does not fit the stored {want}{tuple(stored['shape'])}")
|
||||
writes.append((offsets[key] + stored["data"][0], np.ascontiguousarray(g).tobytes()))
|
||||
shutil.copyfile(path, out)
|
||||
with open(out, "r+b") as f:
|
||||
for offset, data in writes:
|
||||
f.seek(offset)
|
||||
f.write(data)
|
||||
|
||||
|
||||
def main(argv: list[str]) -> int:
|
||||
if len(argv) < 2 or argv[0] not in ("check", "record") or (argv[0] == "record" and len(argv) != 3):
|
||||
print("usage: mock_parity check ARTIFACT... | record ARTIFACT OUT", file=sys.stderr)
|
||||
return 2
|
||||
try:
|
||||
if argv[0] == "record":
|
||||
st = time.perf_counter()
|
||||
record(argv[1], argv[2])
|
||||
print(f"{argv[2]}: check frame recorded on the mock in {time.perf_counter() - st:.0f}s")
|
||||
return 0
|
||||
for path in argv[1:]:
|
||||
st = time.perf_counter()
|
||||
check(path)
|
||||
print(f"{os.path.basename(path)}: bit-identical to its {HARDWARE} check frame on the {'mock' if ON_MOCK else 'device'} ({time.perf_counter() - st:.0f}s)")
|
||||
return 0
|
||||
except ParityError as e:
|
||||
print(f"PARITY FAIL: {e}", file=sys.stderr)
|
||||
return 1
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
sys.exit(main(sys.argv[1:]))
|
||||
@@ -11,7 +11,7 @@ import pickle
|
||||
import numpy as np
|
||||
|
||||
from openpilot.common.basedir import BASEDIR
|
||||
from openpilot.sunnypilot.modeld_v2.frame_fusion import pack_layout, SPLIT_FRAMES
|
||||
from openpilot.sunnypilot.modeld_v2.frame_fusion import host_shapes, pack_layout, SPLIT_FRAMES
|
||||
from openpilot.sunnypilot.modeld_v2.helpers import load_model
|
||||
from openpilot.sunnypilot.modeld_v2.compile_modeld import (POLICY_INPUTS, derive_frame_skip,
|
||||
make_split_input_queues, make_supercombo_input_queues)
|
||||
@@ -174,7 +174,7 @@ class NativeTinygradAdapter(BaseModelAdapter):
|
||||
|
||||
self.input_queues = {name: Tensor(np.zeros(shape, dtype=dtype), device=self.model_device).realize()
|
||||
for name, (shape, dtype) in self.input_shapes.items() if name in self.state_pairs}
|
||||
shapes = {name: shape for name, (shape, _) in self.input_shapes.items() if name not in self.state_pairs and name != 'new_img'}
|
||||
shapes = host_shapes({name: shape for name, (shape, _) in self.input_shapes.items()}, self.state_pairs)
|
||||
offsets, packed = pack_layout(shapes, 0 if self.split else self.warp_frame_size)
|
||||
self.packed_input = np.zeros(packed, dtype=np.uint8)
|
||||
self.host = Tensor(self.packed_input, device='NPY')
|
||||
|
||||
@@ -11,6 +11,7 @@ from functools import partial
|
||||
import gc
|
||||
import os
|
||||
os.environ['GMMU'] = '0'
|
||||
os.environ['QCOM_PRIORITY'] = '1'
|
||||
from tinygrad.device import Device
|
||||
import numpy as np
|
||||
import threading
|
||||
@@ -44,6 +45,7 @@ from openpilot.sunnypilot.modeld_v2.blendful import Blendful
|
||||
from openpilot.sunnypilot.modeld_v2.constants import ModelConstants, 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.light_frame import get_light_warp_matrix
|
||||
from openpilot.sunnypilot.livedelay.helpers import get_lat_delay
|
||||
from openpilot.sunnypilot.modeld_v2.modeld_base import ModelStateBase
|
||||
from openpilot.sunnypilot.modeld_v2.helpers import load_model
|
||||
@@ -171,7 +173,7 @@ class ModelState(ModelStateBase):
|
||||
np.where(inputs[desire_key] - self.prev_desire > .99, inputs[desire_key], 0)
|
||||
self.prev_desire[:] = inputs[desire_key]
|
||||
|
||||
for key in ('traffic_convention', 'lateral_control_params', 'action_t'):
|
||||
for key in ('traffic_convention', 'lateral_control_params', 'action_t', 'speed_limit'):
|
||||
if key in self.numpy_inputs and key in inputs:
|
||||
self.numpy_inputs[key][:] = inputs[key]
|
||||
|
||||
@@ -179,6 +181,8 @@ class ModelState(ModelStateBase):
|
||||
for i, key in enumerate(self._vision_input_names):
|
||||
if key in transforms:
|
||||
self.numpy_inputs['tfm'][i] = transforms[key].reshape(3, 3)
|
||||
if 'light_tfm' in self.numpy_inputs and 'light' in transforms:
|
||||
self.numpy_inputs['light_tfm'][0] = transforms['light'].reshape(3, 3)
|
||||
else:
|
||||
self.numpy_inputs['tfm'][:, :] = transforms[self._road_key].reshape(3, 3)
|
||||
self.numpy_inputs['big_tfm'][:, :] = transforms[self._wide_key].reshape(3, 3)
|
||||
@@ -338,7 +342,7 @@ def main(demo=False):
|
||||
pub_socks = ["modelV2", "drivingModelData", "cameraOdometry", "modelDataV2SP"] + (["chestnutGpuState"] if CHESTNUT else [])
|
||||
pm = PubMaster(pub_socks)
|
||||
sm = SubMaster(["deviceState", "carState", "narrowRoadCameraState", "extrinsicsCalibration", "driverMonitoringState",
|
||||
"carControl", "controlsState", "lateralDelay"])
|
||||
"carControl", "controlsState", "lateralDelay", "longitudinalPlanSP"])
|
||||
|
||||
publish_state = PublishState()
|
||||
chestnut_state = ChestnutGpuState(pm, model.chestnut) if CHESTNUT else None
|
||||
@@ -351,6 +355,7 @@ def main(demo=False):
|
||||
|
||||
model_transform_main = np.zeros((3, 3), dtype=np.float32)
|
||||
model_transform_extra = np.zeros((3, 3), dtype=np.float32)
|
||||
model_transform_light = np.zeros((3, 3), dtype=np.float32)
|
||||
live_calib_seen = False
|
||||
buf_main, buf_extra = None, None
|
||||
meta_main = FrameMeta()
|
||||
@@ -369,6 +374,9 @@ def main(demo=False):
|
||||
prev_action = log.ModelDataV2.Action()
|
||||
|
||||
DH = DesireHelper()
|
||||
desire_frames = [q.shape[0] for m in (model, small_model) if m is not None for name, q in m.adapter.input_queues.items() if 'desire' in name]
|
||||
if desire_frames:
|
||||
DH.turn_repulse = min(desire_frames) - 2
|
||||
meta_constants = load_meta_constants()
|
||||
RELC = RoadEdgeLaneChangeController()
|
||||
blendful = Blendful()
|
||||
@@ -425,6 +433,7 @@ def main(demo=False):
|
||||
model_transform_main = get_warp_matrix(device_from_calib_euler, main_intrinsics, False).astype(np.float32)
|
||||
model_transform_extra = get_warp_matrix(device_from_calib_euler, dc.wide_road.intrinsics, True).astype(np.float32)
|
||||
model_transform_main, model_transform_extra = camera_offset_helper.update(model_transform_main, model_transform_extra, sm, main_wide_camera)
|
||||
model_transform_light = get_light_warp_matrix(device_from_calib_euler, main_intrinsics)
|
||||
live_calib_seen = True
|
||||
|
||||
traffic_convention = np.zeros(2)
|
||||
@@ -446,6 +455,7 @@ def main(demo=False):
|
||||
|
||||
bufs = {name: buf_extra if 'big' in name else buf_main for name in model.vision_input_names}
|
||||
transforms = {name: model_transform_extra if 'big' in name else model_transform_main for name in model.vision_input_names}
|
||||
transforms['light'] = model_transform_light
|
||||
|
||||
frame_delay = DT_MDL # compensate for time passed since the frame was captured: current_time - timestamp_eof is 50ms on average
|
||||
action_delay = DT_MDL / 2 # middle of the interval between model output (current state) and next frame (expected state)
|
||||
@@ -463,6 +473,10 @@ def main(demo=False):
|
||||
if 'action_t' in model.numpy_inputs:
|
||||
inputs['action_t'] = np.array([lat_action_t, long_action_t], dtype=np.float32)
|
||||
|
||||
if 'speed_limit' in model.numpy_inputs:
|
||||
resolver = sm['longitudinalPlanSP'].speedLimit.resolver
|
||||
inputs['speed_limit'] = np.array([resolver.speedLimitFinal if resolver.speedLimitValid else 0.0], dtype=np.float32)
|
||||
|
||||
mt1 = time.perf_counter()
|
||||
try:
|
||||
send_chestnut = (chestnut_state is not None and
|
||||
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:1baac6f02902df5689e9e275633c122a9955b7c57de2681e0137e1724c1f32dd
|
||||
size 3463278
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:0478837491c584b2212e31a91c494a908b8fb048205700f05a02a13ee7fc9b90
|
||||
size 7690094
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:580fadf61ded34b4b19f0ba1f5e4b61c0ea489ca34a0952ccf2878593e3f68c4
|
||||
size 1851239
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:44700f3533abb3e65232c8aca46b48384a59218545ed6bb505c5d4762204359b
|
||||
size 3964263
|
||||
@@ -1,3 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d776c72125156b5dd3eb59768409401e28c8a52a3a619cd3b9f02c10a156fda6
|
||||
oid sha256:1f5dd8855de07d0e8b9ed836934e1dcbe77aa27c3b5c77eee1f21888f974ba8b
|
||||
size 3699072
|
||||
|
||||
@@ -1,3 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:a3f13ed12e087817a86afd48b2496c66c4f61a1925065b676b2945e81fabaacd
|
||||
oid sha256:226d40112a292077b7eca26b97273c56ab3a84feee8ddf9b6d02d46c2a7b8403
|
||||
size 7924864
|
||||
|
||||
@@ -80,7 +80,8 @@ def serialize_jit(jit, kernel_linear, check: dict | None = None) -> tuple[dict,
|
||||
if ast.op is Ops.PROGRAM:
|
||||
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),
|
||||
device_target = dataclasses.asdict(dataclasses.replace(elf.target, interface=elf.target.interface.removeprefix("MOCK")))
|
||||
calls.append({"kind": "program", "name": elf.name, "lib": blob.add(bytes(elf.lib)), "target": device_target,
|
||||
"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})
|
||||
|
||||
@@ -17,4 +17,4 @@ class TestRegistryModels(unittest.TestCase):
|
||||
self.skipTest("MODEL_BASE_NAME env var not set, skipping integration test.")
|
||||
bundle = load_model(os.path.join(os.environ.get("MODEL_DIR", "/tmp/models"), base_name), {"QCOM": "CPU", "AMD": "CPU"}, verify=False, cache=False)
|
||||
jits = [value for value in bundle.values() if isinstance(value, PlainJit)]
|
||||
assert "metadata" in bundle and jits and all(len(jit.captured.linear.src) > 0 for jit in jits)
|
||||
assert "metadata" in bundle and jits and all(len(jit.captured._linear.src) > 0 for jit in jits)
|
||||
|
||||
@@ -112,7 +112,7 @@ class ModelCache:
|
||||
|
||||
class ModelFetcher:
|
||||
"""Handles fetching and caching of model data from remote source"""
|
||||
MODEL_URL = "https://raw.githubusercontent.com/sunnypilot/sunnypilot-models/refs/heads/gh-pages/docs/driving_models_v25.json"
|
||||
MODEL_URL = "https://raw.githubusercontent.com/sunnypilot/sunnypilot-models/refs/heads/gh-pages/docs/driving_models_v26.json"
|
||||
MODEL_URL_CHESTNUT = "https://raw.githubusercontent.com/sunnypilot/sunnypilot-models/refs/heads/gh-pages/docs/driving_models_chestnut_v28.json"
|
||||
|
||||
MODEL_SOURCES = {
|
||||
|
||||
@@ -6,6 +6,7 @@ See the LICENSE.md file in the root directory for more details.
|
||||
"""
|
||||
|
||||
import asyncio
|
||||
import json
|
||||
import os
|
||||
import re
|
||||
import threading
|
||||
@@ -28,8 +29,11 @@ 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_ATTEMPTS = 3 # per piece, before the transfer as a whole is retried
|
||||
PIECE_BACKOFF = 1.0 # seconds, growing linearly: waits 1 s then 2 s between a piece's three attempts
|
||||
DOWNLOAD_ATTEMPTS = 4 # whole-transfer attempts, each resuming from the sidecar
|
||||
RETRY_BACKOFF = 2.0 # seconds, doubling: waits 2, 4 then 8 s between the four transfer attempts
|
||||
RETRY_POLL = 0.25 # how often a backoff checks for a cancel
|
||||
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
|
||||
@@ -49,26 +53,69 @@ def _is_transient(e: BaseException) -> bool:
|
||||
|
||||
|
||||
class _Progress:
|
||||
def __init__(self):
|
||||
self._bytes = 0
|
||||
def __init__(self, done: set[int], done_bytes: int):
|
||||
self._bytes = done_bytes
|
||||
self._done = set(done)
|
||||
self._lock = threading.Lock()
|
||||
|
||||
def add_bytes(self, n: int) -> None:
|
||||
with self._lock:
|
||||
self._bytes += n
|
||||
|
||||
def snapshot(self) -> int:
|
||||
def mark_done(self, index: int) -> None:
|
||||
with self._lock:
|
||||
return self._bytes
|
||||
self._done.add(index)
|
||||
|
||||
def snapshot(self) -> tuple[int, set[int]]:
|
||||
with self._lock:
|
||||
return self._bytes, set(self._done)
|
||||
|
||||
|
||||
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:
|
||||
def _sidecar_path(path: str) -> str:
|
||||
return f"{path}.download"
|
||||
|
||||
|
||||
def _download_in_progress(path: str) -> bool:
|
||||
return os.path.isfile(_sidecar_path(path))
|
||||
|
||||
|
||||
def _save_resume_state(path: str, layout: dict, done: set[int]) -> None:
|
||||
tmp = _sidecar_path(path) + ".tmp"
|
||||
with open(tmp, "w") as f:
|
||||
json.dump({**layout, "done": sorted(done)}, f)
|
||||
f.flush()
|
||||
os.fsync(f.fileno())
|
||||
os.replace(tmp, _sidecar_path(path)) # a power loss leaves the old sidecar or the new one, never a torn file
|
||||
dir_fd = os.open(os.path.dirname(path) or ".", os.O_RDONLY)
|
||||
try:
|
||||
os.fsync(dir_fd)
|
||||
finally:
|
||||
os.close(dir_fd)
|
||||
|
||||
|
||||
def _remove_download_state(path: str) -> None:
|
||||
for stale in (_sidecar_path(path), _sidecar_path(path) + ".tmp"):
|
||||
if os.path.isfile(stale):
|
||||
os.remove(stale)
|
||||
|
||||
|
||||
def _prepare_target(path: str, layout: dict) -> set[int]:
|
||||
total = layout["total"]
|
||||
try:
|
||||
with open(_sidecar_path(path)) as f:
|
||||
state = json.load(f)
|
||||
if isinstance(state, dict) and all(state.get(k) == v for k, v in layout.items()) and os.path.getsize(path) == total:
|
||||
return {i for i in state.get("done", []) if isinstance(i, int)}
|
||||
except (OSError, ValueError, TypeError): # missing, unreadable or malformed sidecar: start over
|
||||
pass
|
||||
_save_resume_state(path, layout, set())
|
||||
with open(path, "wb") as f:
|
||||
f.truncate(total)
|
||||
return set()
|
||||
|
||||
|
||||
def _content_range_total(response: requests.Response) -> int | None:
|
||||
@@ -110,6 +157,9 @@ def _fetch_piece(url: str, path: str, index: int, start: int, end: int | None, p
|
||||
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")
|
||||
f.flush()
|
||||
os.fsync(f.fileno()) # before it is recorded, so a power loss never leaves the sidecar naming unsynced bytes
|
||||
progress.mark_done(index)
|
||||
return
|
||||
except requests.RequestException as e:
|
||||
progress.add_bytes(-written) # the piece restarts from scratch
|
||||
@@ -120,6 +170,11 @@ def _fetch_piece(url: str, path: str, index: int, start: int, end: int | None, p
|
||||
raise DownloadCancelled("Download cancelled") from None
|
||||
|
||||
|
||||
def _remove_file(path: str) -> None:
|
||||
if os.path.isfile(path):
|
||||
os.remove(path)
|
||||
|
||||
|
||||
class ModelManagerSP:
|
||||
"""Manages model downloads and status reporting"""
|
||||
|
||||
@@ -186,11 +241,12 @@ class ModelManagerSP:
|
||||
else:
|
||||
eta = self._calculate_eta(artifact.fileName, progress)
|
||||
self._set_progress(artifact, custom.ModelManagerSP.DownloadStatus.downloading, progress, eta, speed)
|
||||
artifact.downloadProgress.resuming = False # shown only for the first report, when the bar jumps to the resumed point
|
||||
|
||||
async def _report_until_done(self, tasks: list[asyncio.Future], artifact, progress: _Progress, total: int,
|
||||
started: tuple[int, float]) -> None:
|
||||
async def _report_until_done(self, tasks: list[asyncio.Future], artifact, progress: _Progress, path: str, layout: dict,
|
||||
started: tuple[int, set[int], float]) -> None:
|
||||
pending = set(tasks)
|
||||
last_bytes, last_time = started
|
||||
last_bytes, saved, last_time = started
|
||||
speed = 0.0
|
||||
while pending:
|
||||
done, pending = await asyncio.wait(pending, timeout=REPORT_INTERVAL)
|
||||
@@ -199,14 +255,17 @@ class ModelManagerSP:
|
||||
if self._download_interrupted():
|
||||
raise DownloadCancelled("Download cancelled")
|
||||
now = time.monotonic()
|
||||
done_bytes = progress.snapshot()
|
||||
done_bytes, done_pieces = progress.snapshot()
|
||||
if done_pieces != saved:
|
||||
_save_resume_state(path, layout, done_pieces)
|
||||
saved = done_pieces
|
||||
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)
|
||||
self._publish_progress(artifact, done_bytes, layout["total"], speed)
|
||||
|
||||
async def _download_file(self, url: str, path: str, artifact) -> None:
|
||||
self._download_start_times[artifact.fileName] = time.monotonic()
|
||||
@@ -214,16 +273,18 @@ class ModelManagerSP:
|
||||
|
||||
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()
|
||||
layout = {"total": total, "piece_size": PIECE_SIZE, "ranged": ranged, "sha256": artifact.downloadUri.sha256}
|
||||
done = await loop.run_in_executor(None, _prepare_target, path, layout)
|
||||
resumed_bytes = sum(end - start for i, (start, end) in enumerate(pieces) if i in done and end is not None)
|
||||
progress = _Progress(done, resumed_bytes) # the bar and eta start from the resumed pieces
|
||||
cancel = threading.Event()
|
||||
started = progress.snapshot(), time.monotonic() # before any worker can land bytes
|
||||
started = *progress.snapshot(), time.monotonic() # before any worker can land bytes
|
||||
|
||||
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)]
|
||||
for i, (start, end) in enumerate(pieces) if i not in done]
|
||||
try:
|
||||
await self._report_until_done(tasks, artifact, progress, total, started)
|
||||
await self._report_until_done(tasks, artifact, progress, path, layout, started)
|
||||
except BaseException as e:
|
||||
cancel.set()
|
||||
if isinstance(e, DownloadCancelled):
|
||||
@@ -232,9 +293,32 @@ class ModelManagerSP:
|
||||
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)
|
||||
await loop.run_in_executor(None, pool.shutdown) # let running pieces stop so none lands after the save
|
||||
_save_resume_state(path, layout, progress.snapshot()[1])
|
||||
raise
|
||||
|
||||
_remove_download_state(path)
|
||||
artifact.downloadProgress.resuming = False
|
||||
del self._download_start_times[artifact.fileName]
|
||||
|
||||
async def _download_with_retries(self, url: str, path: str, artifact) -> None:
|
||||
for attempt in range(DOWNLOAD_ATTEMPTS):
|
||||
try:
|
||||
await self._download_file(url, path, artifact)
|
||||
return
|
||||
except Exception as e:
|
||||
if not _is_transient(e) or attempt == DOWNLOAD_ATTEMPTS - 1:
|
||||
raise
|
||||
delay = RETRY_BACKOFF * 2 ** attempt
|
||||
cloudlog.warning(f"Retrying {artifact.fileName} in {delay:g}s after {type(e).__name__}: {e}")
|
||||
progress = artifact.downloadProgress
|
||||
self._set_progress(artifact, progress.status, progress.progress, progress.eta, 0.0) # stalled: no speed
|
||||
deadline = time.monotonic() + delay
|
||||
while (remaining := deadline - time.monotonic()) > 0:
|
||||
if self._download_interrupted():
|
||||
raise DownloadCancelled("Download cancelled") from e
|
||||
await asyncio.sleep(min(RETRY_POLL, remaining))
|
||||
|
||||
async def _process_artifact(self, artifact, destination_path: str) -> None:
|
||||
if not artifact.downloadUri.uri:
|
||||
return None
|
||||
@@ -246,37 +330,39 @@ class ModelManagerSP:
|
||||
filename = artifact.fileName
|
||||
full_path = os.path.join(destination_path, filename)
|
||||
status = custom.ModelManagerSP.DownloadStatus
|
||||
artifact.downloadProgress.resuming = False
|
||||
artifact.downloadProgress.canceling = False
|
||||
|
||||
try:
|
||||
self._set_progress(artifact, status.verifying, 0)
|
||||
if await verify_file(full_path, expected_hash):
|
||||
self._set_progress(artifact, status.cached, 100)
|
||||
return
|
||||
if _download_in_progress(full_path):
|
||||
cloudlog.info(f"Resuming interrupted download of {filename}")
|
||||
artifact.downloadProgress.resuming = True
|
||||
else:
|
||||
self._set_progress(artifact, status.verifying, 0)
|
||||
if await verify_file(full_path, expected_hash):
|
||||
self._set_progress(artifact, status.cached, 100)
|
||||
return
|
||||
|
||||
self._set_progress(artifact, status.downloading, 0)
|
||||
await self._download_file(url, full_path, artifact)
|
||||
await self._download_with_retries(url, full_path, artifact)
|
||||
self._set_progress(artifact, status.verifying, 99)
|
||||
if not await verify_file(full_path, expected_hash):
|
||||
_remove_file(full_path)
|
||||
_remove_download_state(full_path)
|
||||
raise ValueError(f"Hash validation failed for {filename}")
|
||||
|
||||
self._set_progress(artifact, status.downloaded, 100)
|
||||
|
||||
except DownloadCancelled:
|
||||
except DownloadCancelled: # not a failure: the request handler clears the row
|
||||
self._download_start_times.pop(artifact.fileName, None)
|
||||
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 = status.failed
|
||||
self._report_status()
|
||||
raise
|
||||
|
||||
except Exception as e:
|
||||
cloudlog.error(f"Error downloading {filename}: {str(e)}")
|
||||
if os.path.isfile(full_path): # noqa: ASYNC240
|
||||
os.remove(full_path)
|
||||
artifact.downloadProgress.status = status.failed
|
||||
artifact.downloadProgress.eta = 0
|
||||
artifact.downloadProgress.speed = 0
|
||||
@@ -333,6 +419,8 @@ class ModelManagerSP:
|
||||
self.params.put(ACTIVE_BUNDLE_KEYS[source], model_bundle.to_dict(), block=True)
|
||||
self.active_bundle = get_active_bundle(self.params, chestnut=self.chestnut_present)
|
||||
|
||||
except DownloadCancelled:
|
||||
raise # not a failure
|
||||
except Exception:
|
||||
if self.selected_bundle is not None:
|
||||
self.selected_bundle.status = custom.ModelManagerSP.DownloadStatus.failed
|
||||
@@ -360,11 +448,14 @@ class ModelManagerSP:
|
||||
self._download_ref = ref_to_download
|
||||
try:
|
||||
self.download(model_to_download, Paths.model_root(), source)
|
||||
except DownloadCancelled:
|
||||
self.selected_bundle = None
|
||||
except Exception as e:
|
||||
cloudlog.exception(e)
|
||||
cloudlog.exception(e) # a failure stays on the row until the next request
|
||||
else:
|
||||
self.selected_bundle = None
|
||||
finally:
|
||||
self._release_download_ref()
|
||||
self.selected_bundle = None
|
||||
|
||||
def main_thread(self) -> None:
|
||||
"""Main thread for model management"""
|
||||
|
||||
@@ -11,11 +11,13 @@ import contextlib
|
||||
import dataclasses
|
||||
import hashlib
|
||||
import http.server
|
||||
import json
|
||||
import math
|
||||
import os
|
||||
import random
|
||||
import re
|
||||
import requests
|
||||
import stat
|
||||
import tempfile
|
||||
import threading
|
||||
import time
|
||||
@@ -55,6 +57,8 @@ class ServerState:
|
||||
fail_ranges: dict[tuple[int, int], int] = dataclasses.field(default_factory=dict) # range -> HTTP status, every time
|
||||
fail_times: dict[tuple[int, int], int] = dataclasses.field(default_factory=dict) # range -> how many more requests 503
|
||||
short_once: set[tuple[int, int]] = dataclasses.field(default_factory=set) # ranges whose first answer is cut short
|
||||
fail_after_others: bool = False # hold each failure until every other piece has been sent
|
||||
sent: set[tuple[int, int]] = dataclasses.field(default_factory=set) # ranges sent in full
|
||||
stall_ranges: set[tuple[int, int]] = dataclasses.field(default_factory=set)
|
||||
stall_event: threading.Event | None = None
|
||||
stall_released_by_event: bool | None = None
|
||||
@@ -88,6 +92,10 @@ class DownloadHandler(http.server.BaseHTTPRequestHandler):
|
||||
state.fail_times[rng] -= 1
|
||||
status = 503
|
||||
if status is not None:
|
||||
others = {piece_range(i) for i in range(NUM_PIECES)} - {rng}
|
||||
deadline = time.monotonic() + 5
|
||||
while state.fail_after_others and not others <= state.sent and time.monotonic() < deadline:
|
||||
time.sleep(0.01)
|
||||
self.send_response(status)
|
||||
self.end_headers()
|
||||
return
|
||||
@@ -115,6 +123,8 @@ class DownloadHandler(http.server.BaseHTTPRequestHandler):
|
||||
self.wfile.write(payload[100:])
|
||||
else:
|
||||
self.wfile.write(payload)
|
||||
if rng is not None:
|
||||
state.sent.add(rng)
|
||||
|
||||
|
||||
@contextlib.contextmanager
|
||||
@@ -133,7 +143,10 @@ def threaded_server(handler):
|
||||
class InlineExecutor(concurrent.futures.Executor):
|
||||
def submit(self, fn, /, *args, **kwargs):
|
||||
future: concurrent.futures.Future = concurrent.futures.Future()
|
||||
future.set_result(fn(*args, **kwargs)) # the piece lands before the reporter starts
|
||||
try:
|
||||
future.set_result(fn(*args, **kwargs)) # the piece lands before the reporter starts
|
||||
except BaseException as e:
|
||||
future.set_exception(e)
|
||||
return future
|
||||
|
||||
|
||||
@@ -147,11 +160,12 @@ class ManagerDownloadTestBase(OpenpilotTestCase):
|
||||
self.addCleanup(self._tmp.cleanup)
|
||||
self.dest = self._tmp.name
|
||||
|
||||
for name, value in (('PIECE_SIZE', PIECE_SIZE), ('REPORT_INTERVAL', 0.05), ('PIECE_BACKOFF', 0.01), ('SPEED_FLOOR', 100)):
|
||||
for name, value in (('PIECE_SIZE', PIECE_SIZE), ('REPORT_INTERVAL', 0.05), ('PIECE_BACKOFF', 0.01), ('SPEED_FLOOR', 100), ('RETRY_BACKOFF', 0.01)):
|
||||
self.enterContext(mock.patch.object(manager_module, name, value))
|
||||
|
||||
self.reported: list[float] = []
|
||||
self.reported_statuses: list[int] = []
|
||||
self.reported_resuming: list[bool] = []
|
||||
|
||||
self.manager = ModelManagerSP.__new__(ModelManagerSP)
|
||||
self.params = self.manager.params = mock.MagicMock()
|
||||
@@ -172,6 +186,7 @@ class ManagerDownloadTestBase(OpenpilotTestCase):
|
||||
self.reported.append(float(artifact.downloadProgress.progress))
|
||||
status = artifact.downloadProgress.status
|
||||
self.reported_statuses.append(getattr(status, 'raw', status)) # .raw: _DynamicEnum equals its int but does not hash like it
|
||||
self.reported_resuming.append(bool(artifact.downloadProgress.resuming))
|
||||
|
||||
def make_artifact(self):
|
||||
bundle = custom.ModelManagerSP.ModelBundle.new_message()
|
||||
@@ -188,6 +203,24 @@ class ManagerDownloadTestBase(OpenpilotTestCase):
|
||||
def path(self) -> str:
|
||||
return os.path.join(self.dest, FILE_NAME)
|
||||
|
||||
@property
|
||||
def sidecar(self) -> str:
|
||||
return manager_module._sidecar_path(self.path)
|
||||
|
||||
def resume_state(self) -> dict:
|
||||
with open(self.sidecar) as f:
|
||||
return json.load(f)
|
||||
|
||||
def write_resume_state(self, done: list[int], total: int = len(WHOLE_BODY), file_size: int | None = None,
|
||||
file_sha256: str = sha256(WHOLE_BODY)) -> None:
|
||||
with open(self.path, 'wb') as f:
|
||||
f.truncate(len(WHOLE_BODY) if file_size is None else file_size)
|
||||
for i in done:
|
||||
f.seek(i * PIECE_SIZE)
|
||||
f.write(WHOLE_BODY[i * PIECE_SIZE:(i + 1) * PIECE_SIZE])
|
||||
with open(self.sidecar, 'w') as f:
|
||||
json.dump({"total": total, "piece_size": PIECE_SIZE, "ranged": True, "sha256": file_sha256, "done": done}, f)
|
||||
|
||||
def piece_requests(self) -> list[tuple[int, int]]:
|
||||
return [r for r in self.server.request_ranges if r is not None and r != (0, 0)]
|
||||
|
||||
@@ -209,6 +242,17 @@ class ManagerDownloadTestBase(OpenpilotTestCase):
|
||||
def download_bundle(self, source: str):
|
||||
asyncio.run(self.manager._download_bundle(self._bundle, self.dest, source))
|
||||
|
||||
def request_download(self) -> dict:
|
||||
self.make_artifact()
|
||||
self._bundle.ref = "ref"
|
||||
self._bundle.minimumSelectorVersion = helpers.REQUIRED_JSON_VERSION
|
||||
self.manager.source_models = {"qcom": [self._bundle], "chestnut": []}
|
||||
self.manager.params, store = self._make_params_with_store()
|
||||
store["ModelManager_DownloadRef"] = "ref"
|
||||
with mock.patch.object(manager_module.Paths, 'model_root', return_value=self.dest):
|
||||
self.manager._process_download_requests()
|
||||
return store
|
||||
|
||||
def read_path(self) -> bytes:
|
||||
with open(self.path, 'rb') as f:
|
||||
return f.read()
|
||||
@@ -225,6 +269,7 @@ class ManagerDownloadTestBase(OpenpilotTestCase):
|
||||
|
||||
params.get.side_effect = get
|
||||
params.put.side_effect = put
|
||||
params.remove.side_effect = lambda key: put(key, None)
|
||||
return params, store
|
||||
|
||||
|
||||
@@ -238,6 +283,7 @@ class TestManagerDownload(ManagerDownloadTestBase):
|
||||
assert max(self.reported) <= 99.0, "progress holds below 100 until the hash check"
|
||||
assert artifact.fileName not in self.manager._download_start_times
|
||||
assert artifact.downloadProgress.speed > 0, "a running download shows its speed"
|
||||
assert not os.path.exists(self.sidecar), "the resume state goes once every piece has landed"
|
||||
|
||||
def test_speed_counts_bytes_landed_before_the_first_report(self):
|
||||
self.enterContext(mock.patch.object(manager_module, 'ThreadPoolExecutor', lambda max_workers: InlineExecutor()))
|
||||
@@ -296,9 +342,42 @@ class TestManagerDownload(ManagerDownloadTestBase):
|
||||
|
||||
def test_permanent_failure_is_not_retried(self):
|
||||
self.server.fail_ranges = {piece_range(1): 404}
|
||||
self.enterContext(mock.patch.object(manager_module, 'ThreadPoolExecutor', lambda max_workers: InlineExecutor()))
|
||||
with self.assertRaises(requests.exceptions.HTTPError):
|
||||
self.download_file()
|
||||
self.process_artifact()
|
||||
assert self.piece_requests().count(piece_range(1)) == 1
|
||||
assert os.path.isfile(self.path)
|
||||
assert self.resume_state()["done"] == [i for i in range(NUM_PIECES) if i != 1]
|
||||
|
||||
def test_failed_transfer_resumes_on_retry(self):
|
||||
self.server.fail_times = {piece_range(1): manager_module.PIECE_ATTEMPTS} # the first transfer gives up on piece 1
|
||||
self.server.fail_after_others = True # by then every other piece is saved
|
||||
self.process_artifact()
|
||||
assert self.read_path() == WHOLE_BODY
|
||||
assert self.piece_requests().count(piece_range(1)) == manager_module.PIECE_ATTEMPTS + 1, "the retry fetched piece 1"
|
||||
others = [i for i in range(NUM_PIECES) if i != 1]
|
||||
assert all(self.piece_requests().count(piece_range(i)) == 1 for i in others), "the retry skipped every saved piece"
|
||||
|
||||
def test_lasting_transient_failure_gives_up(self):
|
||||
self.server.fail_ranges = {piece_range(1): 503}
|
||||
with self.assertRaises(requests.exceptions.HTTPError):
|
||||
self.process_artifact()
|
||||
assert self.piece_requests().count(piece_range(1)) == manager_module.PIECE_ATTEMPTS * manager_module.DOWNLOAD_ATTEMPTS
|
||||
|
||||
def test_cancel_ends_retry_backoff(self):
|
||||
self.enterContext(mock.patch.object(manager_module, 'RETRY_BACKOFF', 30.0))
|
||||
self.manager._download_ref = b"ref"
|
||||
|
||||
def fail_then_cancel(*args):
|
||||
self.params.get.return_value = None # the user cancels while the manager waits to retry
|
||||
raise requests.exceptions.ConnectionError("dropped")
|
||||
transfer = self.enterContext(mock.patch.object(self.manager, '_download_file', side_effect=fail_then_cancel))
|
||||
started = time.monotonic()
|
||||
with self.assertRaises(DownloadCancelled):
|
||||
self.process_artifact()
|
||||
assert time.monotonic() - started < 5, "the wait must end at the cancel, not after 30 s"
|
||||
assert transfer.call_count == 1, "no second transfer after a cancel"
|
||||
assert self.artifact.downloadProgress.status != custom.ModelManagerSP.DownloadStatus.failed
|
||||
|
||||
def test_removing_download_ref_cancels(self):
|
||||
stall_event = self.stall(3)
|
||||
@@ -316,6 +395,51 @@ class TestManagerDownload(ManagerDownloadTestBase):
|
||||
assert self.server.stall_released_by_event is True, "the cancel must have caught the piece mid-transfer"
|
||||
end = piece_range(3)[1] + 1
|
||||
assert self.read_path()[end - 100:end] == bytes(100), "the cancelled piece must stop before its last bytes land"
|
||||
done = self.resume_state()["done"]
|
||||
assert done and 3 not in done, "a cancel records the finished pieces, and only those, for resume"
|
||||
|
||||
def test_resume_skips_complete_pieces(self):
|
||||
self.write_resume_state(done=[0, 4])
|
||||
self.download_file()
|
||||
assert piece_range(0) not in self.piece_requests() and piece_range(4) not in self.piece_requests()
|
||||
assert self.read_path() == WHOLE_BODY
|
||||
assert min(self.reported) >= 2 * PIECE_SIZE / len(WHOLE_BODY) * 100 - 1, "progress must not restart below the resumed share"
|
||||
|
||||
def test_unusable_resume_state_starts_over(self):
|
||||
def malformed(content: bytes):
|
||||
self.write_resume_state(done=[0])
|
||||
with open(self.sidecar, 'wb') as f:
|
||||
f.write(content)
|
||||
|
||||
layout = {"total": len(WHOLE_BODY), "piece_size": PIECE_SIZE, "ranged": True, "sha256": sha256(WHOLE_BODY)}
|
||||
cases = {
|
||||
"other size": lambda: self.write_resume_state(done=[0], total=len(WHOLE_BODY) + 1),
|
||||
"other bytes": lambda: self.write_resume_state(done=[0], file_sha256="0" * 64),
|
||||
"truncated file": lambda: self.write_resume_state(done=[0], file_size=PIECE_SIZE),
|
||||
"not an object": lambda: malformed(b'[]'),
|
||||
"cut-off json": lambda: malformed(b'{"total": '),
|
||||
"done not a list": lambda: malformed(json.dumps({**layout, "done": 3}).encode()),
|
||||
"done not ints": lambda: malformed(json.dumps({**layout, "done": ["0", None]}).encode()),
|
||||
}
|
||||
for name, write_state in cases.items():
|
||||
with self.subTest(name):
|
||||
self.server.request_ranges = []
|
||||
write_state()
|
||||
self.download_file()
|
||||
assert sorted(self.piece_requests()) == [piece_range(i) for i in range(NUM_PIECES)], "every piece is fetched again"
|
||||
assert self.read_path() == WHOLE_BODY
|
||||
|
||||
def test_pieces_and_resume_state_are_synced_to_disk(self):
|
||||
real_fsync, synced = os.fsync, []
|
||||
|
||||
def record_sync(fd):
|
||||
st = os.fstat(fd)
|
||||
synced.append("dir" if stat.S_ISDIR(st.st_mode) else "model" if os.path.exists(self.path) and st.st_ino == os.stat(self.path).st_ino else "sidecar")
|
||||
real_fsync(fd)
|
||||
with mock.patch.object(manager_module.os, 'fsync', side_effect=record_sync):
|
||||
self.download_file()
|
||||
assert synced.count("model") == NUM_PIECES, f"expected one fsync per piece, got {synced.count('model')}"
|
||||
assert "sidecar" in synced and "dir" in synced, "sidecar file and directory must be fsync'd"
|
||||
|
||||
def test_replaced_download_ref_queues_instead_of_canceling(self):
|
||||
self.params.get.return_value = b"other-ref"
|
||||
@@ -345,9 +469,26 @@ class TestProcessArtifact(ManagerDownloadTestBase):
|
||||
self.server.corrupt = True
|
||||
with self.assertRaises(ValueError):
|
||||
self.process_artifact()
|
||||
assert not os.path.isfile(self.path)
|
||||
assert not os.path.isfile(self.path) and not os.path.exists(self.sidecar), "a corrupt file must not be resumed from"
|
||||
assert self.artifact.downloadProgress.status == custom.ModelManagerSP.DownloadStatus.failed
|
||||
|
||||
def test_interrupted_download_resumes_without_reverifying(self):
|
||||
self.write_resume_state(done=[0, 1, 2])
|
||||
artifact = self.process_artifact()
|
||||
ds = custom.ModelManagerSP.DownloadStatus
|
||||
assert self.reported_statuses[0] == ds.downloading, "an in-progress download is not verified first"
|
||||
assert piece_range(0) not in self.piece_requests()
|
||||
assert artifact.downloadProgress.status == ds.downloaded
|
||||
assert any(self.reported_resuming), "a resumed download is flagged resuming until its first progress report"
|
||||
assert not artifact.downloadProgress.resuming
|
||||
|
||||
def test_resume_with_every_piece_done_clears_resuming(self):
|
||||
self.write_resume_state(done=list(range(NUM_PIECES)))
|
||||
artifact = self.process_artifact()
|
||||
assert self.piece_requests() == []
|
||||
assert artifact.downloadProgress.status == custom.ModelManagerSP.DownloadStatus.downloaded
|
||||
assert not artifact.downloadProgress.resuming
|
||||
|
||||
def test_probe_failure_moves_past_verifying(self):
|
||||
self.server.fail_ranges = {(0, 0): 404} # the size probe
|
||||
with self.assertRaises(requests.exceptions.HTTPError):
|
||||
@@ -374,6 +515,23 @@ class TestProcessArtifact(ManagerDownloadTestBase):
|
||||
self.download_bundle("qcom")
|
||||
assert ACTIVE_BUNDLE_KEYS["qcom"] not in store
|
||||
assert os.path.isfile(self.path), "cancel must not delete a cached model"
|
||||
assert self.manager.selected_bundle.status != custom.ModelManagerSP.DownloadStatus.failed, "a cancel is not a failure"
|
||||
|
||||
def test_failed_download_stays_on_the_row(self):
|
||||
self.server.fail_ranges = {piece_range(1): 404}
|
||||
store = self.request_download()
|
||||
selected = self.manager.selected_bundle
|
||||
assert selected is not None and selected.status == custom.ModelManagerSP.DownloadStatus.failed, "a failure stays on the row"
|
||||
assert store["ModelManager_DownloadRef"] is None, "the failed request is released"
|
||||
|
||||
def test_finished_download_clears_the_row(self):
|
||||
self.request_download()
|
||||
assert self.manager.selected_bundle is None
|
||||
|
||||
def test_cancelled_download_clears_the_row(self):
|
||||
self.pm.send.side_effect = lambda *args: self.manager.params.remove("ModelManager_DownloadRef") # cancel at the first report
|
||||
self.request_download()
|
||||
assert self.manager.selected_bundle is None
|
||||
|
||||
def test_download_ref_is_released_only_if_unchanged(self):
|
||||
for current, removed in ((b"new-ref", False), (b"ref", True)):
|
||||
|
||||
@@ -126,7 +126,6 @@ def initialize_params(params) -> list[dict[str, Any]]:
|
||||
keys.extend([
|
||||
"ToyotaEnforceStockLongitudinal",
|
||||
"ToyotaStopAndGoHack",
|
||||
"ToyotaEnhancedBsm",
|
||||
"ToyotaTSS2Smooth",
|
||||
])
|
||||
|
||||
|
||||
@@ -13,7 +13,6 @@ from opendbc.car.subaru.values import CAR as SUBARU_CAR, SubaruFlags
|
||||
from opendbc.car.toyota.values import CAR as TOYOTA_CAR, ToyotaFlags
|
||||
from opendbc.sunnypilot.car.interfaces import has_bsm
|
||||
from opendbc.sunnypilot.car.tesla.values import TeslaFlagsSP
|
||||
from opendbc.sunnypilot.car.toyota.values import ToyotaFlagsSP
|
||||
from openpilot.common.params import Params
|
||||
from openpilot.common.swaglog import cloudlog
|
||||
from openpilot.common.hardware import HARDWARE
|
||||
@@ -45,7 +44,6 @@ CAPABILITY_FIELDS = (
|
||||
"device_type",
|
||||
"subaru_has_sng",
|
||||
"hyundai_alpha_long_available",
|
||||
"toyota_enhanced_bsm_available",
|
||||
"toyota_tss2",
|
||||
"custom_model_active",
|
||||
)
|
||||
@@ -70,7 +68,6 @@ CAPABILITY_LABELS: dict[str, str] = {
|
||||
"device_type": "Device type",
|
||||
"subaru_has_sng": "Subaru Stop-and-Go available",
|
||||
"hyundai_alpha_long_available": "Hyundai Alpha Longitudinal available",
|
||||
"toyota_enhanced_bsm_available": "Toyota Enhanced BSM available",
|
||||
"toyota_tss2": "Toyota TSS2 platform",
|
||||
"custom_model_active": "Non-Default model selected",
|
||||
}
|
||||
@@ -92,7 +89,6 @@ CAR_CAPABILITY_FIELDS = (
|
||||
"subaru_has_sng",
|
||||
"hyundai_alpha_long_available",
|
||||
"toyota_tss2",
|
||||
"toyota_enhanced_bsm_available",
|
||||
)
|
||||
|
||||
# Explicit defaults for non-boolean capability fields
|
||||
@@ -108,7 +104,7 @@ def _bundle_field(bundle: dict | None, key: str) -> str:
|
||||
return bundle.get(key, "") if isinstance(bundle, dict) else ""
|
||||
|
||||
|
||||
def _resolve_brand_capabilities(caps: dict, bundle_platform: str, CP, CP_SP=None) -> None:
|
||||
def _resolve_brand_capabilities(caps: dict, bundle_platform: str, CP) -> None:
|
||||
"""Set brand-specific capabilities from bundle platform or CarParams fallback.
|
||||
|
||||
Bundle (manual car selection) is a pre-fingerprint approximation.
|
||||
@@ -142,19 +138,11 @@ def _resolve_brand_capabilities(caps: dict, bundle_platform: str, CP, CP_SP=None
|
||||
elif brand == "toyota":
|
||||
if bundle_platform:
|
||||
try:
|
||||
flags = TOYOTA_CAR[bundle_platform].config.flags
|
||||
caps["toyota_tss2"] = bool(flags & ToyotaFlags.TSS2)
|
||||
caps["toyota_enhanced_bsm_available"] = bool(flags & ToyotaFlags.TSS2) and not bool(flags & ToyotaFlags.SECOC)
|
||||
caps["toyota_tss2"] = bool(TOYOTA_CAR[bundle_platform].config.flags & ToyotaFlags.TSS2)
|
||||
except KeyError:
|
||||
cloudlog.exception(f"capabilities: unknown toyota platform {bundle_platform!r}")
|
||||
elif CP is not None:
|
||||
caps["toyota_tss2"] = bool(CP.flags & ToyotaFlags.TSS2)
|
||||
# same gate as _initialize_toyota: openpilot longitudinal, not SecOC, and either TSS2 or a
|
||||
# smartDSU. The bundle path can't see 0x2FF or longitudinal, so it stays TSS2-only.
|
||||
sdsu_bsm = CP_SP is not None and bool(CP_SP.flags & ToyotaFlagsSP.SMART_DSU)
|
||||
caps["toyota_enhanced_bsm_available"] = (bool(CP.openpilotLongitudinalControl) and
|
||||
not bool(CP.flags & ToyotaFlags.SECOC) and
|
||||
(bool(CP.flags & ToyotaFlags.TSS2) or sdsu_bsm))
|
||||
|
||||
|
||||
def generate_capabilities(params: Params | None = None) -> dict:
|
||||
@@ -229,7 +217,7 @@ def generate_capabilities(params: Params | None = None) -> dict:
|
||||
if CP is not None:
|
||||
caps["has_bsm"] = has_bsm(CP, CP_SP)
|
||||
|
||||
_resolve_brand_capabilities(caps, bundle_platform, CP, CP_SP)
|
||||
_resolve_brand_capabilities(caps, bundle_platform, CP)
|
||||
|
||||
return caps
|
||||
|
||||
|
||||
@@ -156,7 +156,7 @@ The tables below describe the **compiled** `settings_ui.json` schema — what th
|
||||
|
||||
**Enablement rules**: Grayed out (disabled) when rules fail. Frontend shows a contextual badge explaining why.
|
||||
|
||||
**Capability fields** (referenced in rules): `has_longitudinal_control`, `has_icbm`, `icbm_available`, `torque_allowed`, `brand`, `pcm_cruise`, `alpha_long_available`, `steer_control_type`, `has_bsm`, `is_release`, `is_sp_release`, `is_development`, `tesla_has_vehicle_bus`, `has_stop_and_go`, `stock_longitudinal`, `toyota_enhanced_bsm_available`
|
||||
**Capability fields** (referenced in rules): `has_longitudinal_control`, `has_icbm`, `icbm_available`, `torque_allowed`, `brand`, `pcm_cruise`, `alpha_long_available`, `steer_control_type`, `has_bsm`, `is_release`, `is_sp_release`, `is_development`, `tesla_has_vehicle_bus`, `has_stop_and_go`, `stock_longitudinal`
|
||||
|
||||
---
|
||||
|
||||
|
||||
@@ -2361,28 +2361,6 @@
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"key": "ToyotaEnhancedBsm",
|
||||
"widget": "toggle",
|
||||
"needs_onroad_cycle": true,
|
||||
"title": "Enhanced Blind Spot Monitoring (Alpha)",
|
||||
"description": "sunnypilot will poll the blind spot monitor diagnostics directly from the radar. Use this on vehicles whose blind spot monitors do not report blind spot status over the standard CAN signals. This is an alpha feature. Use at your own risk.",
|
||||
"enablement": [
|
||||
{
|
||||
"type": "not_engaged"
|
||||
},
|
||||
{
|
||||
"type": "capability",
|
||||
"field": "toyota_enhanced_bsm_available",
|
||||
"equals": true
|
||||
},
|
||||
{
|
||||
"type": "capability",
|
||||
"field": "stock_longitudinal",
|
||||
"equals": false
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"key": "ToyotaTSS2Smooth",
|
||||
"widget": "toggle",
|
||||
|
||||
@@ -101,21 +101,6 @@ sections:
|
||||
- type: param
|
||||
key: ToyotaEnforceStockLongitudinal
|
||||
equals: false
|
||||
- key: ToyotaEnhancedBsm
|
||||
widget: toggle
|
||||
needs_onroad_cycle: true
|
||||
title: Enhanced Blind Spot Monitoring (Alpha)
|
||||
description: sunnypilot will poll the blind spot monitor diagnostics directly from the radar. Use this on vehicles whose
|
||||
blind spot monitors do not report blind spot status over the standard CAN signals. This is an alpha feature. Use at
|
||||
your own risk.
|
||||
enablement:
|
||||
- $ref: '#/macros/not_engaged'
|
||||
- type: capability
|
||||
field: toyota_enhanced_bsm_available
|
||||
equals: true
|
||||
- type: capability
|
||||
field: stock_longitudinal
|
||||
equals: false
|
||||
- key: ToyotaTSS2Smooth
|
||||
widget: toggle
|
||||
needs_onroad_cycle: true
|
||||
|
||||
@@ -70,18 +70,12 @@ class TestOpaquePerBrandFlags(OpenpilotTestCase):
|
||||
def test_hyundai_alpha_long_available_field_present(self):
|
||||
assert "hyundai_alpha_long_available" in CAPABILITY_FIELDS
|
||||
|
||||
def test_toyota_enhanced_bsm_available_field_present(self):
|
||||
assert "toyota_enhanced_bsm_available" in CAPABILITY_FIELDS
|
||||
|
||||
def test_subaru_has_sng_default_false(self, caps):
|
||||
assert caps["subaru_has_sng"] is False
|
||||
|
||||
def test_hyundai_alpha_long_available_default_false(self, caps):
|
||||
assert caps["hyundai_alpha_long_available"] is False
|
||||
|
||||
def test_toyota_enhanced_bsm_available_default_false(self, caps):
|
||||
assert caps["toyota_enhanced_bsm_available"] is False
|
||||
|
||||
def test_toyota_tss2_field_present(self):
|
||||
assert "toyota_tss2" in CAPABILITY_FIELDS
|
||||
|
||||
|
||||
@@ -207,7 +207,6 @@ class TestNotEngagedReplacement(OpenpilotTestCase):
|
||||
"AlphaLongitudinalEnabled",
|
||||
"ToyotaEnforceStockLongitudinal",
|
||||
"ToyotaStopAndGoHack",
|
||||
"ToyotaEnhancedBsm",
|
||||
"ToyotaTSS2Smooth",
|
||||
], names=["key"])
|
||||
def test_offroad_only_replaced_with_not_engaged(self, schema, key):
|
||||
|
||||
@@ -286,7 +286,6 @@ class TestKnownVehicleSettings(OpenpilotTestCase):
|
||||
keys = {i["key"] for i in _brand_items(schema["vehicle_settings"].get("toyota"))}
|
||||
assert "ToyotaEnforceStockLongitudinal" in keys
|
||||
assert "ToyotaStopAndGoHack" in keys
|
||||
assert "ToyotaEnhancedBsm" in keys
|
||||
assert "ToyotaTSS2Smooth" in keys
|
||||
|
||||
def test_tesla_has_coop_steering(self, schema):
|
||||
|
||||
+1
-1
Submodule tinygrad_repo updated: 92b742f711...301a0d1ded
Reference in New Issue
Block a user