mirror of
https://github.com/sunnypilot/sunnypilot.git
synced 2026-11-13 04:43:43 +08:00
Compare commits
5 Commits
emu
..
fix-qcom-warp
| Author | SHA1 | Date | |
|---|---|---|---|
 discountchubbs
|
3cfe730f8c | ||
|
discountchubbs
|
6d34938afe | ||
|
Jason Wen
|
61af0a0512 | ||
|
github-actions[bot]
|
066c0e2957 | ||
|
Jason Wen
|
26b8501e7b |
@@ -34,11 +34,6 @@ 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
|
||||
@@ -112,11 +107,6 @@ 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
|
||||
@@ -140,7 +130,6 @@ 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:
|
||||
|
||||
@@ -1,61 +0,0 @@
|
||||
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: ${{ steps.key.outputs.key }}
|
||||
|
||||
- name: Already passed
|
||||
if: steps.passed.outputs.cache-hit == 'true'
|
||||
shell: bash
|
||||
run: |
|
||||
echo "LS2 rebuild skipped: it already matched the chestnut runner's build with this exact mock, converter, LLVM and python"
|
||||
@@ -42,7 +42,7 @@ jobs:
|
||||
WARP_PKL="openpilot/sunnypilot/modeld_v2/models/driving_warp_${res}_tinygrad.pkl"
|
||||
echo "Compiling $WARP_PKL on QCOM"
|
||||
taskset -c 7 env DEV=QCOM IMAGE=1 FLOAT16=1 NOLOCALS=1 JIT_BATCH_SIZE=0 OPENPILOT_HACKS=1 python3 openpilot/sunnypilot/modeld_v2/compile_warp.py \
|
||||
--frame ${FRAME_PARAM} --warp-to ${MODEL_SIZE} --output "${WARP_PKL}"
|
||||
--frame ${FRAME_PARAM} --warp-to ${MODEL_SIZE} --split-frames --output "${WARP_PKL}"
|
||||
|
||||
BIG_WARP_PKL="openpilot/sunnypilot/modeld_v2/models/big_driving_warp_${res}_tinygrad.pkl"
|
||||
echo "Compiling $BIG_WARP_PKL on AMD"
|
||||
|
||||
@@ -1,60 +0,0 @@
|
||||
name: Set up tinygrad's amd mock
|
||||
description: LLVM 20 and ROCm comgr, as tinygrad_repo/.github/actions/setup-tinygrad installs them for the mock gpu
|
||||
inputs:
|
||||
emu_cache:
|
||||
description: >-
|
||||
Keep tinygrad's cache db (the emulator's compiled kernels and gate results) between runs under this name, e.g. the model's file name.
|
||||
Empty: no cache.
|
||||
default: ''
|
||||
runs:
|
||||
using: composite
|
||||
steps:
|
||||
- name: Install LLVM 20 and ROCm comgr
|
||||
shell: bash
|
||||
run: |
|
||||
. /etc/os-release
|
||||
curl -fsSL https://apt.llvm.org/llvm-snapshot.gpg.key | sudo tee /etc/apt/trusted.gpg.d/apt.llvm.org.asc > /dev/null
|
||||
echo "deb http://apt.llvm.org/$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/**') }}-
|
||||
@@ -35,11 +35,6 @@ 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:
|
||||
@@ -64,11 +59,6 @@ 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 }}]
|
||||
@@ -163,74 +153,18 @@ jobs:
|
||||
if-no-files-found: error
|
||||
|
||||
build_model:
|
||||
runs-on: ${{ inputs.on_device && fromJSON(inputs.target_hardware == 'chestnut' && '["self-hosted","chestnut"]' || '["self-hosted","tici"]') || 'ubuntu-24.04' }}
|
||||
runs-on: [self-hosted, "${{ inputs.target_hardware == 'chestnut' && 'chestnut' || 'tici' }}"]
|
||||
needs: get_model
|
||||
env:
|
||||
MODEL_NAME: ${{ inputs.custom_name || inputs.upstream_branch }} (${{ needs.get_model.outputs.model_date }})
|
||||
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
|
||||
env:
|
||||
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') }}
|
||||
run: |
|
||||
MARKER="ci/qcom-compiler-parity/$(printf '%s' "$KEY" | tr -c 'A-Za-z0-9._-' '_').txt"
|
||||
CODE=$(curl -s -o /dev/null -w '%{http_code}' -I -L "https://huggingface.co/datasets/sunnypilot/sunnypilot_models_v1/resolve/main/$MARKER")
|
||||
echo "$MARKER: HTTP $CODE"
|
||||
{ echo "key=$KEY"; echo "marker=$MARKER"; echo "passed=$([ "$CODE" = 200 ] && echo true || echo false)"; } >> "$GITHUB_OUTPUT"
|
||||
|
||||
- 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.passed != '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"
|
||||
|
||||
- name: Remember the compiler check passed
|
||||
if: env.MOCK_BUILD == 'true' && inputs.target_hardware != 'chestnut' && steps.qcom_compiler.outputs.passed != 'true'
|
||||
env:
|
||||
HF_TOKEN: ${{ secrets.HF_TOKEN }}
|
||||
KEY: ${{ steps.qcom_compiler.outputs.key }}
|
||||
MARKER: ${{ steps.qcom_compiler.outputs.marker }}
|
||||
run: |
|
||||
python3 -m pip install -q --upgrade "huggingface_hub>=0.34"
|
||||
printf '%s\n%s\n' "$KEY" "$GITHUB_SERVER_URL/$GITHUB_REPOSITORY/actions/runs/$GITHUB_RUN_ID" > "$RUNNER_TEMP/marker.txt"
|
||||
hf upload --repo-type dataset sunnypilot/sunnypilot_models_v1 "$RUNNER_TEMP/marker.txt" "$MARKER" \
|
||||
--commit-message "qcom compiler parity passed: $KEY" || echo "::warning::could not record the pass, the next build checks again"
|
||||
|
||||
- name: Set environment variables
|
||||
if: env.MOCK_BUILD != 'true'
|
||||
id: set-env
|
||||
run: |
|
||||
# Set up common environment
|
||||
@@ -243,7 +177,6 @@ jobs:
|
||||
printenv >> $GITHUB_ENV
|
||||
|
||||
- name: Setup build environment
|
||||
if: env.MOCK_BUILD != 'true'
|
||||
run: |
|
||||
mkdir -p "${BUILD_DIR}/"
|
||||
sudo find $BUILD_DIR/ -mindepth 1 -delete
|
||||
@@ -265,28 +198,21 @@ jobs:
|
||||
|
||||
- name: Build Model
|
||||
run: |
|
||||
if [ "$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 ${UV_PROJECT_ENVIRONMENT}/bin/activate
|
||||
TASKSET="taskset -c 7"
|
||||
fi
|
||||
source /etc/profile
|
||||
export UV_PROJECT_ENVIRONMENT=${HOME}/venv
|
||||
export VIRTUAL_ENV=$UV_PROJECT_ENVIRONMENT
|
||||
source ${UV_PROJECT_ENVIRONMENT}/bin/activate
|
||||
export PYTHONPATH="${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=$(python3 -c "from openpilot.common.transformations.camera import _ar_ox_fisheye as a, _os_fisheye as o; print(f'{a.width}x{a.height} {o.width}x{o.height}')")
|
||||
|
||||
MOCK=$([ "$MOCK_BUILD" = "true" ] && echo MOCK || true)
|
||||
TG_FLAGS_QCOM="DEV=${MOCK:+MOCK+}QCOM IMAGE=1 FLOAT16=1 NOLOCALS=1 OPENPILOT_HACKS=1"
|
||||
TG_FLAGS_QCOM="DEV=QCOM IMAGE=1 FLOAT16=1 NOLOCALS=1 OPENPILOT_HACKS=1"
|
||||
if [ "${{ inputs.target_hardware }}" == "chestnut" ]; then
|
||||
echo "CHESTNUT build"
|
||||
export CHESTNUT=1
|
||||
TG_FLAGS="DEBUG=1 DEV=${MOCK}USB+AMD:LLVM FRAME_DEV=CPU FLOAT16=1 GMMU=0 TC_OPT=2 TC_MIN_GLOBALS=32"
|
||||
TG_FLAGS="DEBUG=1 DEV=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"
|
||||
@@ -301,16 +227,14 @@ 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"
|
||||
$ON_MOCK env DEV=USB+AMD PYTHONPATH="$UPSTREAM_TG:${{ github.workspace }}" $TASKSET python3 openpilot/sunnypilot/modeld_v2/convert_upstream_pkl.py \
|
||||
env DEV=USB+AMD PYTHONPATH="$UPSTREAM_TG:${{ github.workspace }}" taskset -c 7 python3 openpilot/sunnypilot/modeld_v2/convert_upstream_pkl.py \
|
||||
"${{ 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 python3 openpilot/sunnypilot/modeld_v2/compile_modeld_v2.py \
|
||||
env ${TG_FLAGS} taskset -c 7 python3 openpilot/sunnypilot/modeld_v2/compile_modeld_v2.py \
|
||||
"$NEW_ARCH_ONNX" "$OUTPUT_PKL" --device-input "*" --benchmark-runs 1
|
||||
else
|
||||
echo "Detected onnx architecture. Routing to native compile_modeld.py."
|
||||
@@ -360,7 +284,7 @@ jobs:
|
||||
|
||||
if [ -n "$MODEL_TYPE" ]; then
|
||||
echo "Detected: $MODEL_TYPE -> $OUTPUT_PKL"
|
||||
env ${TG_FLAGS} $TASKSET python3 "$COMPILE_MODELD" \
|
||||
env ${TG_FLAGS} taskset -c 7 python3 "$COMPILE_MODELD" \
|
||||
--model-type $MODEL_TYPE \
|
||||
--model-size $MODEL_SIZE \
|
||||
--camera-resolutions $CAMERA_RES \
|
||||
@@ -369,13 +293,6 @@ 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 ${{ env.OUTPUT_DIR }}
|
||||
@@ -387,7 +304,7 @@ jobs:
|
||||
--include='/${{ inputs.target_hardware == 'chestnut' && 'big_' || '' }}driving_tinygrad.pkl' \
|
||||
--exclude='*' \
|
||||
--delete-excluded \
|
||||
$([ "$MOCK_BUILD" = "true" ] || echo --chown=comma:comma) \
|
||||
--chown=comma:comma \
|
||||
${{ env.MODELS_DIR }}/ ${{ env.OUTPUT_DIR }}/
|
||||
|
||||
python3 "${{ github.workspace }}/release/ci/model_generator.py" \
|
||||
@@ -416,7 +333,7 @@ jobs:
|
||||
path: ${{ env.OUTPUT_DIR }}/artifact_name.txt
|
||||
|
||||
- name: Re-enable powersave
|
||||
if: always() && env.MOCK_BUILD != 'true'
|
||||
if: always()
|
||||
run: |
|
||||
source ${UV_PROJECT_ENVIRONMENT}/bin/activate
|
||||
PYTHONPATH=$PYTHONPATH:${{ github.workspace }}/ ${{ github.workspace }}/scripts/manage-powersave.py --enable
|
||||
|
||||
@@ -28,7 +28,18 @@ jobs:
|
||||
env:
|
||||
DEV: CPU
|
||||
run: tools/op.sh test -v openpilot/sunnypilot/modeld_v2/tests/test_plain_artifact.py
|
||||
- uses: ./.github/workflows/setup-amd-mock
|
||||
- name: Install LLVM 20 and ROCm comgr for the amd mock, as tinygrad_repo/.github/actions/setup-tinygrad does
|
||||
run: |
|
||||
. /etc/os-release
|
||||
curl -fsSL https://apt.llvm.org/llvm-snapshot.gpg.key | sudo tee /etc/apt/trusted.gpg.d/apt.llvm.org.asc > /dev/null
|
||||
echo "deb http://apt.llvm.org/$VERSION_CODENAME/ llvm-toolchain-$VERSION_CODENAME-20 main" | sudo tee /etc/apt/sources.list.d/llvm.list
|
||||
sudo mkdir -p /etc/apt/keyrings
|
||||
curl -fsSL https://repo.radeon.com/rocm/rocm.gpg.key | gpg --dearmor | sudo tee /etc/apt/keyrings/rocm.gpg > /dev/null
|
||||
echo "deb [arch=amd64 signed-by=/etc/apt/keyrings/rocm.gpg] https://repo.radeon.com/rocm/apt/7.1 $VERSION_CODENAME main" | sudo tee /etc/apt/sources.list.d/rocm.list
|
||||
printf 'Package: *\nPin: release o=repo.radeon.com\nPin-Priority: 600\n' | sudo tee /etc/apt/preferences.d/rocm-pin-600
|
||||
sudo apt-get -qq update && sudo apt-get -qq install -y --no-install-recommends libllvm20 clang-20 lld-20 comgr
|
||||
printf '/opt/rocm/lib\n/opt/rocm/lib64\n' | sudo tee /etc/ld.so.conf.d/rocm.conf && sudo ldconfig
|
||||
echo "/usr/lib/llvm-20/bin" >> "$GITHUB_PATH"
|
||||
- name: Convert a pickled USB+AMD jit and replay it under tinygrad's amd mock
|
||||
env:
|
||||
DEV: MOCKUSB+AMD
|
||||
@@ -69,8 +80,6 @@ jobs:
|
||||
runs-on: ubuntu-latest
|
||||
outputs:
|
||||
models: ${{ steps.set-matrix.outputs.models }}
|
||||
chestnut: ${{ steps.set-matrix.outputs.chestnut }}
|
||||
qcom: ${{ steps.set-matrix.outputs.qcom }}
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
- name: Fetch and Parse json
|
||||
@@ -82,22 +91,16 @@ jobs:
|
||||
with open("openpilot/sunnypilot/models/fetcher.py", "r") as f:
|
||||
urls = re.findall(r"MODEL_URL(?:_CHESTNUT)?\s*=\s*[\"'"'"']([^\"'"'"']+)[\"'"'"']", f.read())
|
||||
|
||||
artifacts, chestnut, qcom = [], [], []
|
||||
artifacts = []
|
||||
for url in urls:
|
||||
data = json.loads(urllib.request.urlopen(url).read())
|
||||
for bundle in data.get("bundles", []):
|
||||
for model in bundle.get("models", []):
|
||||
if "artifact" in model:
|
||||
artifacts.append(model["artifact"])
|
||||
if "chestnut" in url:
|
||||
chestnut.append(model["artifact"])
|
||||
elif "tinygrad" in model["artifact"]["file_name"]:
|
||||
qcom.append(model["artifact"])
|
||||
|
||||
with open(os.environ["GITHUB_OUTPUT"], "a") as f:
|
||||
f.write(f"models={json.dumps(artifacts)}\n")
|
||||
f.write(f"chestnut={json.dumps(chestnut)}\n")
|
||||
f.write(f"qcom={json.dumps(qcom)}\n")
|
||||
'
|
||||
|
||||
test-model:
|
||||
@@ -134,81 +137,3 @@ jobs:
|
||||
export PYTHONPATH="$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
-1
@@ -4,7 +4,7 @@
|
||||
|
||||
A supported vehicle is one that just works when you install a comma device. All supported cars provide a better experience than any stock system. Supported vehicles reference the US market unless otherwise specified.
|
||||
|
||||
# 351 Supported Cars
|
||||
# 354 Supported Cars
|
||||
|
||||
|Make|Model|Supported Package|ACC|No ACC accel below|No ALC below|Steering Torque|Resume from stop|<a href="##"><img width=2000></a>Hardware Needed<br> |Video|Setup Video|
|
||||
|---|---|---|:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|
|
||||
@@ -153,18 +153,21 @@ A supported vehicle is one that just works when you install a comma device. All
|
||||
|Hyundai|Sonata 2018-19|Smart Cruise Control (SCC)|Stock|0 mph|0 mph|[](##)|[](##)|<details><summary>Parts</summary><sub>- 1 Hyundai E connector<br>- 1 OBD-C cable (2 ft)<br>- 1 comma four<br>- 1 comma power v3<br>- 1 harness box<br>- 1 mount<br><a href="https://comma.ai/shop/comma-3x?harness=Hyundai Sonata 2018-19">Buy Here</a></sub></details>|||
|
||||
|Hyundai|Sonata 2020-23|All|openpilot available[<sup>1</sup>](#footnotes)|0 mph|0 mph|[](##)|[](##)|<details><summary>Parts</summary><sub>- 1 Hyundai A connector<br>- 1 OBD-C cable (2 ft)<br>- 1 comma four<br>- 1 comma power v3<br>- 1 harness box<br>- 1 mount<br><a href="https://comma.ai/shop/comma-3x?harness=Hyundai Sonata 2020-23">Buy Here</a></sub></details>|<a href="https://www.youtube.com/watch?v=ix63r9kE3Fw" target="_blank"><img height="18px" src="assets/icon-youtube.svg" /></a>||
|
||||
|Hyundai|Sonata Hybrid 2020-23|All|openpilot available[<sup>1</sup>](#footnotes)|0 mph|0 mph|[](##)|[](##)|<details><summary>Parts</summary><sub>- 1 Hyundai A connector<br>- 1 OBD-C cable (2 ft)<br>- 1 comma four<br>- 1 comma power v3<br>- 1 harness box<br>- 1 mount<br><a href="https://comma.ai/shop/comma-3x?harness=Hyundai Sonata Hybrid 2020-23">Buy Here</a></sub></details>|||
|
||||
|Hyundai|Sonata Hybrid (without HDA II) 2024-26|Smart Cruise Control (SCC)|openpilot available[<sup>1</sup>](#footnotes)|0 mph|0 mph|[](##)|[](##)|<details><summary>Parts</summary><sub>- 1 Hyundai A connector<br>- 1 OBD-C cable (2 ft)<br>- 1 comma four<br>- 1 comma power v3<br>- 1 harness box<br>- 1 mount<br><a href="https://comma.ai/shop/comma-3x?harness=Hyundai Sonata Hybrid (without HDA II) 2024-26">Buy Here</a></sub></details>|||
|
||||
|Hyundai|Staria 2023|All|openpilot available[<sup>1</sup>](#footnotes)|0 mph|0 mph|[](##)|[](##)|<details><summary>Parts</summary><sub>- 1 Hyundai K connector<br>- 1 OBD-C cable (2 ft)<br>- 1 comma four<br>- 1 comma power v3<br>- 1 harness box<br>- 1 mount<br><a href="https://comma.ai/shop/comma-3x?harness=Hyundai Staria 2023">Buy Here</a></sub></details>|||
|
||||
|Hyundai|Tucson 2021|Smart Cruise Control (SCC)|openpilot available[<sup>1</sup>](#footnotes)|19 mph|0 mph|[](##)|[](##)|<details><summary>Parts</summary><sub>- 1 Hyundai L connector<br>- 1 OBD-C cable (2 ft)<br>- 1 comma four<br>- 1 comma power v3<br>- 1 harness box<br>- 1 mount<br><a href="https://comma.ai/shop/comma-3x?harness=Hyundai Tucson 2021">Buy Here</a></sub></details>|||
|
||||
|Hyundai|Tucson 2022|Smart Cruise Control (SCC)|openpilot available[<sup>1</sup>](#footnotes)|0 mph|0 mph|[](##)|[](##)|<details><summary>Parts</summary><sub>- 1 Hyundai N connector<br>- 1 OBD-C cable (2 ft)<br>- 1 comma four<br>- 1 comma power v3<br>- 1 harness box<br>- 1 mount<br><a href="https://comma.ai/shop/comma-3x?harness=Hyundai Tucson 2022">Buy Here</a></sub></details>|||
|
||||
|Hyundai|Tucson 2023-24|All|openpilot available[<sup>1</sup>](#footnotes)|0 mph|0 mph|[](##)|[](##)|<details><summary>Parts</summary><sub>- 1 Hyundai N connector<br>- 1 OBD-C cable (2 ft)<br>- 1 comma four<br>- 1 comma power v3<br>- 1 harness box<br>- 1 mount<br><a href="https://comma.ai/shop/comma-3x?harness=Hyundai Tucson 2023-24">Buy Here</a></sub></details>|||
|
||||
|Hyundai|Tucson Diesel 2019|Smart Cruise Control (SCC)|openpilot available[<sup>1</sup>](#footnotes)|0 mph|0 mph|[](##)|[](##)|<details><summary>Parts</summary><sub>- 1 Hyundai L connector<br>- 1 OBD-C cable (2 ft)<br>- 1 comma four<br>- 1 comma power v3<br>- 1 harness box<br>- 1 mount<br><a href="https://comma.ai/shop/comma-3x?harness=Hyundai Tucson Diesel 2019">Buy Here</a></sub></details>|||
|
||||
|Hyundai|Tucson Hybrid 2022-24|All|openpilot available[<sup>1</sup>](#footnotes)|0 mph|0 mph|[](##)|[](##)|<details><summary>Parts</summary><sub>- 1 Hyundai N connector<br>- 1 OBD-C cable (2 ft)<br>- 1 comma four<br>- 1 comma power v3<br>- 1 harness box<br>- 1 mount<br><a href="https://comma.ai/shop/comma-3x?harness=Hyundai Tucson Hybrid 2022-24">Buy Here</a></sub></details>|||
|
||||
|Hyundai|Tucson Hybrid (without HDA II) 2025-26|Smart Cruise Control (SCC)|openpilot available[<sup>1</sup>](#footnotes)|0 mph|0 mph|[](##)|[](##)|<details><summary>Parts</summary><sub>- 1 Hyundai N connector<br>- 1 OBD-C cable (2 ft)<br>- 1 comma four<br>- 1 comma power v3<br>- 1 harness box<br>- 1 mount<br><a href="https://comma.ai/shop/comma-3x?harness=Hyundai Tucson Hybrid (without HDA II) 2025-26">Buy Here</a></sub></details>|||
|
||||
|Hyundai|Tucson Plug-in Hybrid 2024|All|openpilot available[<sup>1</sup>](#footnotes)|0 mph|0 mph|[](##)|[](##)|<details><summary>Parts</summary><sub>- 1 Hyundai N connector<br>- 1 OBD-C cable (2 ft)<br>- 1 comma four<br>- 1 comma power v3<br>- 1 harness box<br>- 1 mount<br><a href="https://comma.ai/shop/comma-3x?harness=Hyundai Tucson Plug-in Hybrid 2024">Buy Here</a></sub></details>|||
|
||||
|Hyundai|Veloster 2019-20|Smart Cruise Control (SCC)|Stock|5 mph|0 mph|[](##)|[](##)|<details><summary>Parts</summary><sub>- 1 Hyundai E connector<br>- 1 OBD-C cable (2 ft)<br>- 1 comma four<br>- 1 comma power v3<br>- 1 harness box<br>- 1 mount<br><a href="https://comma.ai/shop/comma-3x?harness=Hyundai Veloster 2019-20">Buy Here</a></sub></details>|||
|
||||
|Jeep|Grand Cherokee 2016-18|Adaptive Cruise Control (ACC)|Stock|0 mph|9 mph|[](##)|[](##)|<details><summary>Parts</summary><sub>- 1 FCA connector<br>- 1 OBD-C cable (2 ft)<br>- 1 comma four<br>- 1 comma power v3<br>- 1 harness box<br>- 1 mount<br><a href="https://comma.ai/shop/comma-3x?harness=Jeep Grand Cherokee 2016-18">Buy Here</a></sub></details>|<a href="https://www.youtube.com/watch?v=eLR9o2JkuRk" target="_blank"><img height="18px" src="assets/icon-youtube.svg" /></a>||
|
||||
|Jeep|Grand Cherokee 2019-21|Adaptive Cruise Control (ACC)|Stock|0 mph|39 mph|[](##)|[](##)|<details><summary>Parts</summary><sub>- 1 FCA connector<br>- 1 OBD-C cable (2 ft)<br>- 1 comma four<br>- 1 comma power v3<br>- 1 harness box<br>- 1 mount<br><a href="https://comma.ai/shop/comma-3x?harness=Jeep Grand Cherokee 2019-21">Buy Here</a></sub></details>|||
|
||||
|Kia|Carnival 2022-24|Smart Cruise Control (SCC)|openpilot available[<sup>1</sup>](#footnotes)|0 mph|0 mph|[](##)|[](##)|<details><summary>Parts</summary><sub>- 1 Hyundai A connector<br>- 1 OBD-C cable (2 ft)<br>- 1 comma four<br>- 1 comma power v3<br>- 1 harness box<br>- 1 mount<br><a href="https://comma.ai/shop/comma-3x?harness=Kia Carnival 2022-24">Buy Here</a></sub></details>|||
|
||||
|Kia|Carnival (China only) 2023|Smart Cruise Control (SCC)|openpilot available[<sup>1</sup>](#footnotes)|0 mph|0 mph|[](##)|[](##)|<details><summary>Parts</summary><sub>- 1 Hyundai K connector<br>- 1 OBD-C cable (2 ft)<br>- 1 comma four<br>- 1 comma power v3<br>- 1 harness box<br>- 1 mount<br><a href="https://comma.ai/shop/comma-3x?harness=Kia Carnival (China only) 2023">Buy Here</a></sub></details>|||
|
||||
|Kia|Carnival Hybrid (with HDA II) 2025-26|Highway Driving Assist II|openpilot available[<sup>1</sup>](#footnotes)|0 mph|0 mph|[](##)|[](##)|<details><summary>Parts</summary><sub>- 1 Hyundai Q connector<br>- 1 OBD-C cable (2 ft)<br>- 1 comma four<br>- 1 comma power v3<br>- 1 harness box<br>- 1 mount<br><a href="https://comma.ai/shop/comma-3x?harness=Kia Carnival Hybrid (with HDA II) 2025-26">Buy Here</a></sub></details>|||
|
||||
|Kia|Ceed 2019-21|Smart Cruise Control (SCC)|Stock|0 mph|0 mph|[](##)|[](##)|<details><summary>Parts</summary><sub>- 1 Hyundai E connector<br>- 1 OBD-C cable (2 ft)<br>- 1 comma four<br>- 1 comma power v3<br>- 1 harness box<br>- 1 mount<br><a href="https://comma.ai/shop/comma-3x?harness=Kia Ceed 2019-21">Buy Here</a></sub></details>|||
|
||||
|Kia|Ceed Plug-in Hybrid 2021|Smart Cruise Control (SCC)|Stock|0 mph|0 mph|[](##)|[](##)|<details><summary>Parts</summary><sub>- 1 Hyundai B connector<br>- 1 OBD-C cable (2 ft)<br>- 1 comma four<br>- 1 comma power v3<br>- 1 harness box<br>- 1 mount<br><a href="https://comma.ai/shop/comma-3x?harness=Kia Ceed Plug-in Hybrid 2021">Buy Here</a></sub></details>|||
|
||||
|Kia|EV6 (Southeast Asia only) 2022-24|All|openpilot available[<sup>1</sup>](#footnotes)|0 mph|0 mph|[](##)|[](##)|<details><summary>Parts</summary><sub>- 1 Hyundai P connector<br>- 1 OBD-C cable (2 ft)<br>- 1 comma four<br>- 1 comma power v3<br>- 1 harness box<br>- 1 mount<br><a href="https://comma.ai/shop/comma-3x?harness=Kia EV6 (Southeast Asia only) 2022-24">Buy Here</a></sub></details>|||
|
||||
|
||||
+1
-1
Submodule opendbc_repo updated: 48611ae9d6...f087f898a1
@@ -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')) and not os.getenv('DEV', '').startswith('MOCK'):
|
||||
if 'USB' in os.getenv('DEV', '') or os.getenv('CHESTNUT'):
|
||||
from openpilot.system.hardware.chestnut.flash import link_up
|
||||
for _ in range(10):
|
||||
if link_up():
|
||||
|
||||
@@ -17,16 +17,24 @@ 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("--split-frames", action="store_true", help="one input per camera (frame, big_frame), bound to the camera buffers by pointer")
|
||||
args = parser.parse_args()
|
||||
|
||||
from examples.openpilot.compile_warp import make_frame_prepare, parse_frame, parse_size
|
||||
from tinygrad import Device, Tensor, TinyJit
|
||||
frame = parse_frame(args.frame)
|
||||
warp = make_frame_prepare(frame, *parse_size(args.warp_to))
|
||||
run = TinyJit(lambda input_frame, M_inv: Tensor.stack(*(warp(input_frame[i], M_inv[i]) for i in range(2))), prune=True)
|
||||
rng = np.random.default_rng(42)
|
||||
inputs = {"input_frame": Tensor(rng.integers(0, 256, (2, frame.size), dtype=np.uint8), device=Device.DEFAULT).realize(),
|
||||
"M_inv": Tensor((rng.standard_normal((2, 3, 3)) * 8).astype(np.float32), device=Device.DEFAULT).realize()}
|
||||
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()
|
||||
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 = dict.fromkeys(("frame", "big_frame"), ((frame.size,), "|u1", Device.DEFAULT))
|
||||
else:
|
||||
run = TinyJit(lambda input_frame, M_inv: Tensor.stack(*(warp(input_frame[i], M_inv[i]) for i in range(2))), prune=True)
|
||||
inputs = {"input_frame": Tensor(frames, device=Device.DEFAULT).realize(), "M_inv": m_inv}
|
||||
specs = {"input_frame": ((2, frame.size), "|u1", Device.DEFAULT)}
|
||||
with record_kernel_linear() as recorded:
|
||||
run(**inputs)
|
||||
run(**inputs)
|
||||
@@ -34,7 +42,7 @@ def main():
|
||||
assert len(recorded) == 1, f"expected one captured kernel list, got {len(recorded)}"
|
||||
part = serialize_jit(run, recorded[0], check)
|
||||
PlainJit(*part)
|
||||
specs = {"input_frame": ((2, frame.size), "|u1", Device.DEFAULT), "M_inv": ((2, 3, 3), "<f4", Device.DEFAULT)}
|
||||
specs |= {"M_inv": ((2, 3, 3), "<f4", Device.DEFAULT)}
|
||||
write_bundle(args.output, {"run": part}, {"input_specs": specs, "metadata": {}})
|
||||
print(f"Saved warp to {args.output} ({len(part[0]['calls'])} kernels)")
|
||||
|
||||
|
||||
@@ -10,7 +10,6 @@ import dataclasses
|
||||
import inspect
|
||||
import itertools
|
||||
import mmap
|
||||
import os
|
||||
import re
|
||||
import struct
|
||||
import tempfile
|
||||
@@ -195,8 +194,7 @@ 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]
|
||||
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,
|
||||
calls.append({"kind": "program", "name": re.sub(r"\x1b\[[0-9;]*m", "", kernel[1]), "lib": programs[image_alloc], "target": dataclasses.asdict(target),
|
||||
"signature": [[f"data{i}", i, u8, [a.get("nbytes", 1)]] for i, a in enumerate(args)], "global_size": grid, "local_size": local,
|
||||
"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}
|
||||
@@ -237,16 +235,14 @@ def main():
|
||||
frame, _ = capture_frame(artifact["run"], kwargs, "output_buffers")
|
||||
part = convert(artifact["run"], kwargs, frame, Device[Device.DEFAULT].renderer.target)
|
||||
|
||||
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"
|
||||
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"
|
||||
write_bundle(args.output, {"run": part}, {key: artifact[key] for key in ("metadata", "input_specs", "output_specs")})
|
||||
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}")
|
||||
print(f"converted {len(part[0]['calls'])} kernels, bit-exact with the pickle: {args.output}")
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
|
||||
@@ -20,6 +20,9 @@ def pack_layout(shapes: dict[str, tuple], frame_size: int) -> tuple[dict[str, in
|
||||
return offsets | {"frames": offset}, offset + 2 * frame_size
|
||||
|
||||
|
||||
SPLIT_FRAMES = ("big_frame", "frame") # a --split-frames warp: one input per camera, bound by pointer, not packed into host
|
||||
|
||||
|
||||
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):
|
||||
self.blobs, self.starts = blobs, list(itertools.accumulate([0] + [len(blob) for blob in blobs[:-1]]))
|
||||
@@ -39,29 +42,31 @@ def frame_part(warp_path: str, parts: dict, extras: dict) -> dict:
|
||||
(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_size = next(s["numel"] for s in warp["inputs"] if s["name"] == "input_frame") // 2
|
||||
offsets, packed = pack_layout(host, frame_size)
|
||||
frame_specs = {s["name"]: s for s in warp["inputs"] if s["name"] in SPLIT_FRAMES}
|
||||
frame_size = next(s["numel"] for s in warp["inputs"] if s["name"] in ("input_frame", "frame")) // (1 if frame_specs else 2)
|
||||
offsets, packed = pack_layout(host, 0 if frame_specs else frame_size)
|
||||
shift, upload, u8 = len(model_blob), len(model["buffers"]) + len(warp["buffers"]), repr(_dtype("dtypes.uint8"))
|
||||
|
||||
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)
|
||||
names = sorted(["host", *states])
|
||||
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]
|
||||
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
|
||||
view(s["name"], s["numel"] * _dtype(s["dtype"]).itemsize, s["dtype"]) for s in model["inputs"]}
|
||||
warp_inputs = {s["slot"]: view("frames" if s["name"] == "input_frame" else "tfm", s["numel"] * _dtype(s["dtype"]).itemsize, s["dtype"])
|
||||
for s in warp["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 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 {}) |
|
||||
{"args": [dict(inputs[a["input"]]) if "input" in a else a | {"buffer": a["buffer"] + buffers} for a in call["args"]]} for call in calls]
|
||||
header = {"input_names": names, "returns": {"kind": "NoneType", "tensors": []}, "check": None,
|
||||
"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": 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"]] +
|
||||
[{"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")}]}] +
|
||||
|
||||
@@ -270,16 +270,42 @@ def _program_uop(call: dict, lib: bytes):
|
||||
UOp(Ops.SOURCE, arg=""), UOp(Ops.BINARY, arg=lib)), arg=info)
|
||||
|
||||
|
||||
def _input_key(args: tuple, kwargs: dict) -> tuple | None: # the realized buffers a call binds, by name; None when it can't be reused
|
||||
from tinygrad import Tensor
|
||||
if args:
|
||||
return None
|
||||
key = []
|
||||
for name, value in sorted(kwargs.items()):
|
||||
if not isinstance(value, (Tensor, dict)):
|
||||
return None
|
||||
for sub, tensor in [(None, value)] if isinstance(value, Tensor) else sorted(value.items()):
|
||||
if not isinstance(tensor, Tensor) or not tensor.uop.is_realized:
|
||||
return None
|
||||
key.append((name, sub, tensor.uop))
|
||||
return tuple(key)
|
||||
|
||||
|
||||
class _Jit:
|
||||
def __init__(self, captured, input_names: list, buffers: list):
|
||||
self.captured, self.input_names, self.buffers = captured, input_names, buffers
|
||||
|
||||
def __getstate__(self):
|
||||
return {k: v for k, v in self.__dict__.items() if k != "_bound"}
|
||||
|
||||
def __call__(self, *args, **kwargs):
|
||||
import tinygrad.engine.jit as jit
|
||||
input_uops, var_vals, names, _ = jit._prepare_jit_inputs(args, kwargs)
|
||||
if names != self.input_names:
|
||||
raise ValueError(f"expected inputs {self.input_names}, got {names}")
|
||||
return self.captured(input_uops, var_vals)
|
||||
# modeld binds the same buffers every frame (the camera buffers cycle through a few): bind each set once, not per call
|
||||
bound, key = self.__dict__.setdefault("_bound", {}), _input_key(args, kwargs)
|
||||
if key is None or (hit := bound.get(key)) is None:
|
||||
input_uops, var_vals, names, _ = jit._prepare_jit_inputs(args, kwargs)
|
||||
if names != self.input_names:
|
||||
raise ValueError(f"expected inputs {self.input_names}, got {names}")
|
||||
hit = (input_uops, var_vals)
|
||||
if key is not None:
|
||||
if len(bound) >= 16:
|
||||
bound.clear()
|
||||
bound[key] = hit
|
||||
return self.captured(*hit)
|
||||
|
||||
|
||||
class PlainJit(_Jit):
|
||||
|
||||
@@ -1,153 +0,0 @@
|
||||
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
|
||||
from openpilot.sunnypilot.modeld_v2.frame_fusion import 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)
|
||||
@@ -169,16 +169,18 @@ class NativeTinygradAdapter(BaseModelAdapter):
|
||||
self.warp_frame_size = self.frame_copy_size
|
||||
self._init_common()
|
||||
self.run_model = self.jits['run']
|
||||
self.split = [name for name in SPLIT_FRAMES if name in self.run_model.input_names] # the warp reads the camera buffers in place
|
||||
self.frame_inputs: dict[str, Tensor] = {}
|
||||
|
||||
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'}
|
||||
offsets, packed = pack_layout(shapes, self.warp_frame_size)
|
||||
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')
|
||||
self.numpy_inputs = {name: np.ndarray(shape, dtype=np.float32, buffer=self.packed_input, offset=offsets[name])
|
||||
for name, shape in ({'tfm': (2, 3, 3)} | shapes).items()}
|
||||
self.frames = self.packed_input[offsets['frames']:].reshape(2, self.warp_frame_size)
|
||||
self.frames = None if self.split else self.packed_input[offsets['frames']:].reshape(2, self.warp_frame_size)
|
||||
|
||||
self.outputs = {name: Tensor(np.zeros(shape, dtype=dtype), device=device).realize() for name, (shape, dtype, device) in self.jits['output_specs'].items()}
|
||||
for name, next_name in self.state_pairs.items():
|
||||
@@ -187,17 +189,30 @@ class NativeTinygradAdapter(BaseModelAdapter):
|
||||
|
||||
def copy_frames(self, bufs):
|
||||
for i, key in enumerate(self._vision_input_names):
|
||||
if key in bufs:
|
||||
if key not in bufs:
|
||||
continue
|
||||
if not self.split:
|
||||
data = bufs[key].data if hasattr(bufs[key], 'data') else bufs[key]
|
||||
np.copyto(self.frames[i], np.frombuffer(data, dtype=np.uint8, count=self.warp_frame_size))
|
||||
elif (name := ('frame', 'big_frame')[i]) in self.split:
|
||||
if not hasattr(bufs[key], 'data'): # a numpy frame (warmup, tests): cached memory the GPU must not read in place, so upload it
|
||||
self.frame_inputs[name] = Tensor(np.ascontiguousarray(bufs[key][:self.warp_frame_size]), device=self.model_device).realize()
|
||||
continue
|
||||
ptr = np.frombuffer(bufs[key].data, dtype=np.uint8).ctypes.data # visionipc buffers are coherent: map once per buffer, no copy
|
||||
if (key, ptr) not in self._blob_cache:
|
||||
self._blob_cache[(key, ptr)] = Tensor.from_blob(ptr, (self.warp_frame_size,), dtype='uint8', device=self.model_device)
|
||||
self.frame_inputs[name] = self._blob_cache[(key, ptr)]
|
||||
|
||||
def reset_warmup_buffers(self) -> None:
|
||||
self.packed_input[:] = 0
|
||||
self.frame_inputs.clear()
|
||||
self._blob_cache.clear()
|
||||
self.run_model.__dict__.pop('_bound', None) # warmup's uploaded frames: drop their bindings with them
|
||||
for key in self.state_pairs:
|
||||
self.input_queues[key].assign(0).realize()
|
||||
|
||||
def run(self):
|
||||
self.run_model(host=self.host, **self.input_queues, output_buffers=self.outputs)
|
||||
self.run_model(host=self.host, **self.input_queues, **self.frame_inputs, output_buffers=self.outputs)
|
||||
return self.outputs['outputs']
|
||||
|
||||
|
||||
|
||||
@@ -1,3 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:4b22fd6bcb3a3e8a642e6866449dd9c30c12e694ff0741cad9e34e4b00d8c5fa
|
||||
size 3698799
|
||||
oid sha256:d776c72125156b5dd3eb59768409401e28c8a52a3a619cd3b9f02c10a156fda6
|
||||
size 3699072
|
||||
|
||||
@@ -1,3 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:9a17fd6acece4fab23784ef0f3f8bba28a049e9599e5e9e5ee7b36e4b1d24a6f
|
||||
size 7924847
|
||||
oid sha256:a3f13ed12e087817a86afd48b2496c66c4f61a1925065b676b2945e81fabaacd
|
||||
size 7924864
|
||||
|
||||
@@ -80,8 +80,7 @@ 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({})
|
||||
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,
|
||||
calls.append({"kind": "program", "name": elf.name, "lib": blob.add(bytes(elf.lib)), "target": dataclasses.asdict(elf.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)
|
||||
|
||||
@@ -144,6 +144,21 @@ class TestPlainArtifact(OpenpilotTestCase):
|
||||
for name in ("outputs", "next_state_feat_q"):
|
||||
assert np.array_equal(inputs["output_buffers"][name].numpy(), expected["output_buffers"][name].numpy()), name
|
||||
|
||||
split_path = os.path.join(self.tmp.name, "warp_split_tinygrad.pkl")
|
||||
with mock.patch.object(sys, "argv", ["compile_warp", "--frame", FRAME, "--warp-to", f"{MODEL_W}x{MODEL_H}", "--output", split_path, "--split-frames"]):
|
||||
compile_warp.main()
|
||||
split = load_model(path, cache=False, extend=functools.partial(frame_part, split_path))
|
||||
assert split["run"].input_names == ["big_frame", "frame", "host", "state_feat_q"]
|
||||
offsets, packed = pack_layout(HOST, 0)
|
||||
host = np.zeros(packed, np.uint8)
|
||||
for name, shape in ({"tfm": (2, 3, 3)} | HOST).items():
|
||||
np.ndarray(shape, np.float32, host, offsets[name])[...] = tfm.numpy() if name == "tfm" else inputs[name].numpy()
|
||||
out = {"outputs": Tensor.zeros(OUT).contiguous().realize(), "next_state_feat_q": Tensor.zeros(STATE).contiguous().realize()}
|
||||
split["run"](host=Tensor(host, device="NPY"), frame=Tensor(frames.numpy()[0]).realize(), big_frame=Tensor(frames.numpy()[1]).realize(),
|
||||
state_feat_q=expected["state_feat_q"], output_buffers=out)
|
||||
for name in ("outputs", "next_state_feat_q"): # the camera buffers bound in place give the packed upload's result exactly
|
||||
assert np.array_equal(out[name].numpy(), expected["output_buffers"][name].numpy()), name
|
||||
|
||||
def test_tinygrad_api_the_loader_reads(self):
|
||||
import tinygrad.engine.jit as jit
|
||||
from tinygrad.device import Buffer, TinyELF
|
||||
|
||||
+1
-1
Submodule tinygrad_repo updated: 30ddfc2eac...92b742f711
Reference in New Issue
Block a user