Tinygrad runner (#34261)

* squash

* dmonitoringmodeld: use cl transform (#34235)

* needs cleanup

* only if tici

* bump tinygrad

* check width

* base modelframe

* .

* need to be args

* more cleanup

* no _frame in base

* tici only

* its DrivingModelFrame

* .6 is fair

---------

Co-authored-by: Comma Device <device@comma.ai>

* Update tinygrad

* tg upstream

* bump tg

* bump tg

* debug

* attr

* misc cleanup

* whitespace

* remove

* Add TODOs to make python proc for modelrunners

* whitespace

---------

Co-authored-by: ZwX1616 <zwx1616@gmail.com>
Co-authored-by: Comma Device <device@comma.ai>
Co-authored-by: Maxime Desroches <desroches.maxime@gmail.com>
This commit is contained in:
Harald Schäfer
2024-12-18 11:58:59 -08:00
committed by GitHub
parent ff97a43c50
commit 17ca6389e1
39 changed files with 175 additions and 1483 deletions

View File

@@ -13,20 +13,6 @@ common_src = [
"transforms/transform.cc",
]
thneed_src_common = [
"thneed/thneed_common.cc",
"thneed/serialize.cc",
]
thneed_src_qcom = thneed_src_common + ["thneed/thneed_qcom2.cc"]
thneed_src_pc = thneed_src_common + ["thneed/thneed_pc.cc"]
thneed_src = thneed_src_qcom if arch == "larch64" else thneed_src_pc
# SNPE except on Mac and ARM Linux
snpe_lib = []
if arch != "Darwin" and arch != "aarch64":
common_src += ['runners/snpemodel.cc']
snpe_lib += ['SNPE']
# OpenCL is a framework on Mac
if arch == "Darwin":
@@ -45,34 +31,24 @@ snpe_rpath_pc = f"{Dir('#').abspath}/third_party/snpe/x86_64-linux-clang"
snpe_rpath = lenvCython['RPATH'] + [snpe_rpath_qcom if arch == "larch64" else snpe_rpath_pc]
cython_libs = envCython["LIBS"] + libs
snpemodel_lib = lenv.Library('snpemodel', ['runners/snpemodel.cc'])
commonmodel_lib = lenv.Library('commonmodel', common_src)
lenvCython.Program('runners/runmodel_pyx.so', 'runners/runmodel_pyx.pyx', LIBS=cython_libs, FRAMEWORKS=frameworks)
lenvCython.Program('runners/snpemodel_pyx.so', 'runners/snpemodel_pyx.pyx', LIBS=[snpemodel_lib, snpe_lib, *cython_libs], FRAMEWORKS=frameworks, RPATH=snpe_rpath)
lenvCython.Program('models/commonmodel_pyx.so', 'models/commonmodel_pyx.pyx', LIBS=[commonmodel_lib, *cython_libs], FRAMEWORKS=frameworks)
tinygrad_files = ["#"+x for x in glob.glob(env.Dir("#tinygrad_repo").relpath + "/**", recursive=True, root_dir=env.Dir("#").abspath)]
tinygrad_files = ["#"+x for x in glob.glob(env.Dir("#tinygrad_repo").relpath + "/**", recursive=True, root_dir=env.Dir("#").abspath) if 'pycache' not in x]
# Get model metadata
fn = File("models/supercombo").abspath
cmd = f'python3 {Dir("#selfdrive/modeld").abspath}/get_model_metadata.py {fn}.onnx'
lenv.Command(fn + "_metadata.pkl", [fn + ".onnx"] + tinygrad_files, cmd)
# Build thneed model
if arch == "larch64" or GetOption('pc_thneed'):
tinygrad_opts = []
if not GetOption('pc_thneed'):
# use FLOAT16 on device for speed + don't cache the CL kernels for space
tinygrad_opts += ["FLOAT16=1", "PYOPENCL_NO_CACHE=1"]
cmd = f"cd {Dir('#').abspath}/tinygrad_repo && " + ' '.join(tinygrad_opts) + f" python3 openpilot/compile2.py {fn}.onnx {fn}.thneed"
# Compile tinygrad model
pythonpath_string = 'PYTHONPATH="${PYTHONPATH}:' + env.Dir("#tinygrad_repo").abspath + '"'
if arch == 'larch64':
device_string = 'QCOM=1'
else:
device_string = 'CLANG=1 IMAGE=0'
lenv.Command(fn + ".thneed", [fn + ".onnx"] + tinygrad_files, cmd)
for model_name in ['supercombo', 'dmonitoring_model']:
fn = File(f"models/{model_name}").abspath
cmd = f'{pythonpath_string} {device_string} python3 {Dir("#tinygrad_repo").abspath}/examples/openpilot/compile3.py {fn}.onnx {fn}_tinygrad.pkl'
lenv.Command(fn + "_tinygrad.pkl", [fn + ".onnx"] + tinygrad_files, cmd)
fn_dm = File("models/dmonitoring_model").abspath
cmd = f"cd {Dir('#').abspath}/tinygrad_repo && " + ' '.join(tinygrad_opts) + f" python3 openpilot/compile2.py {fn_dm}.onnx {fn_dm}.thneed"
lenv.Command(fn_dm + ".thneed", [fn_dm + ".onnx"] + tinygrad_files, cmd)
thneed_lib = env.SharedLibrary('thneed', thneed_src, LIBS=[gpucommon, common, 'OpenCL', 'dl'])
thneedmodel_lib = env.Library('thneedmodel', ['runners/thneedmodel.cc'])
lenvCython.Program('runners/thneedmodel_pyx.so', 'runners/thneedmodel_pyx.pyx', LIBS=envCython["LIBS"]+[thneedmodel_lib, thneed_lib, gpucommon, common, 'dl', 'OpenCL'])