pytorch
b6b17e9a
- Merge branch 'main' of github.com:pytorch/pytorch into Switch-Linux-arm64-Runners
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Commit
View On
GitHub
Previous Change (CTRL+↑)
Next Change (CTRL+↓)
Expand Context Lines
Collapse Context Lines
Hide Minimap (CTRL+M)
Commit
1 year ago
Merge branch 'main' of github.com:pytorch/pytorch into Switch-Linux-arm64-Runners
Author
DanilBaibak
Parents
21d86aa2
6f8eecfb
Files
726
.ci
docker
ci_commit_pins
triton-rocm.txt
common
install_onnx.sh
requirements-ci.txt
pytorch
common_utils.sh
multigpu-test.sh
test.sh
.github
actions/filter-test-configs
action.yml
ci_commit_pins
huggingface.txt
vision.txt
xla.txt
requirements
pip-requirements-macOS.txt
scripts
build_triton_wheel.py
comment_on_pr.py
run_torchbench.py
test_trymerge.py
trymerge.py
templates
upload.yml.j2
workflows
_binary-build-linux.yml
_binary-upload.yml
_rocm-test.yml
build-triton-wheel.yml
docker-builds.yml
docker-release.yml
generated-linux-aarch64-binary-manywheel-nightly.yml
generated-linux-binary-conda-nightly.yml
generated-linux-binary-libtorch-cxx11-abi-nightly.yml
generated-linux-binary-libtorch-pre-cxx11-nightly.yml
generated-linux-binary-manywheel-nightly.yml
generated-macos-arm64-binary-conda-nightly.yml
generated-macos-arm64-binary-wheel-nightly.yml
generated-macos-binary-conda-nightly.yml
generated-macos-binary-libtorch-cxx11-abi-nightly.yml
generated-macos-binary-wheel-nightly.yml
generated-windows-binary-conda-nightly.yml
generated-windows-binary-libtorch-debug-nightly.yml
generated-windows-binary-libtorch-release-nightly.yml
generated-windows-binary-wheel-nightly.yml
nightly-rockset-uploads.yml
periodic.yml
run_torchbench.yml
slow.yml
trunk.yml
update_s3_htmls.yml
upload-alerts.yml
upload-test-stats.yml
upload-torch-dynamo-perf-stats.yml
.lintrunner.toml
CODEOWNERS
README.md
RELEASE.md
aten/src/ATen
Dispatch.h
EmptyTensor.h
core
TensorBase.h
boxing/impl
make_boxed_from_unboxed_functor.h
ivalue.h
jit_type.h
op_registration
infer_schema.h
cpu/vec
vec256/vsx
vec256_int16_vsx.h
vec256_int32_vsx.h
vec256_int64_vsx.h
vec_half.h
cuda
CUDABlas.cpp
CUDAGraph.cpp
CUDAGraph.h
detail
CUDAHooks.cpp
CUDAHooks.h
detail
CUDAHooksInterface.h
mps
EmptyTensor.cpp
native
Copy.cpp
DilatedMaxPool3d.cpp
DispatchStub.cpp
DispatchStub.h
LinearAlgebra.cpp
NonSymbolicBC.h
Pool.h
RNN.cpp
SparseTensorUtils.cpp
SpectralOps.cpp
TensorConversions.cpp
TensorConversions.h
TensorShape.cpp
cpu
Activation.cpp
BinaryOpsKernel.cpp
ComplexKernel.cpp
DepthwiseConvKernel.cpp
DistributionKernels.cpp
FlashAttentionKernel.cpp
MaxPoolKernel.cpp
PaddingKernel.cpp
PowKernel.cpp
README.md
ReduceOpsKernel.cpp
SoftMaxKernel.cpp
SumKernel.cpp
UnaryOpsKernel.cpp
cuda
CuFFTPlanCache.h
FusedAdamKernel.cu
FusedAdamWKernel.cu
ReflectionPad.cu
ReplicationPadding.cu
SpectralOps.cpp
fused_adam_amsgrad_impl.cu
fused_adam_amsgrad_impl.cuh
fused_adam_impl.cu
fused_adam_impl.cuh
fused_adam_utils.cuh
fused_adamw_amsgrad_impl.cu
fused_adamw_amsgrad_impl.cuh
fused_adamw_impl.cu
fused_adamw_impl.cuh
layer_norm_kernel.cu
mkldnn
Conv.cpp
MKLDNNCommon.cpp
Utils.cpp
mps
OperationUtils.h
operations
BinaryKernel.mm
BinaryOps.mm
ReduceOps.mm
native_functions.yaml
quantized
cpu
OnednnUtils.h
Pooling.cpp
kernels
QuantizedOpKernels.cpp
qconv.cpp
qconv_prepack.cpp
qembeddingbag.cpp
qembeddingbag_prepack.cpp
qembeddingbag_prepack.h
qembeddingbag_unpack.cpp
qlinear.cpp
qlinear_prepack.cpp
cudnn
utils.h
library.cpp
sparse
SparseCsrTensor.cpp
SparseCsrTensorMath.cpp
SparseTensor.cpp
SparseTensorMath.cpp
SparseUnaryOps.cpp
cuda
SparseSemiStructuredLinear.cu
cuSPARSELtOps.cpp
cutlass
README.md
default_epilogue_tensor_op_row_broadcast.h
default_gemm_sparse_row_broadcast.h
gemm_sparse_row_broadcast.h
predicated_tile_iterator_row_broadcast.h
sparse_gemm_row_broadcast.h
transformers/cuda/mem_eff_attention
kernel_backward.h
kernel_forward.h
ops
from_blob.h
templates
Functions.cpp
test
vec_test_all_types.cpp
benchmarks/dynamo
ci_expected_accuracy
inductor_torchbench_inference.csv
common.py
c10
core
ConstantSymNodeImpl.cpp
ConstantSymNodeImpl.h
Device.h
LargeNegativeIntSymNodeImpl.h
Scalar.h
SingletonSymNodeImpl.cpp
SingletonSymNodeImpl.h
Storage.h
SymBool.cpp
SymBool.h
SymInt.cpp
SymInt.h
SymNodeImpl.h
cuda
CUDACachingAllocator.cpp
CUDAFunctions.cpp
CUDAFunctions.h
test/core
SymInt_test.cpp
util
Half-inl.h
caffe2
ideep/operators/quantization
int8_fully_connected_op.cc
python
core.py
cmake
Modules
FindMKLDNN.cmake
public
mkldnn.cmake
docs/source
_static/img/torch_cuda_memory
active_memory_timeline.png
allocator_state_history.png
community
persons_of_interest.rst
data.rst
export.rst
index.rst
named_tensor.rst
notes
autograd.rst
cuda.rst
onnx.rst
onnx_diagnostics.rst
scripts
exportdb
generate_example_rst.py
onnx
build_onnx_diagnostics_rules_md.py
sparse.rst
tensors.rst
torch_cuda_memory.rst
functorch
csrc/dim
dim.cpp
experimental
_map.py
control_flow.py
writing_batching_rules.md
requirements.txt
test
distributed
_tensor
test_device_mesh.py
test_dtensor.py
test_dtensor_compile.py
fsdp
test_fsdp_backward_prefetch.py
test_fsdp_hybrid_shard.py
tensor/parallel
test_fsdp_2d_parallel.py
test_c10d_nccl.py
test_fake_pg.py
dynamo
test_activation_checkpointing.py
test_aot_autograd.py
test_autograd_function.py
test_exc.py
test_export.py
test_higher_order_ops.py
test_logging.py
test_misc.py
test_modules.py
test_profiler.py
test_repros.py
test_subclasses.py
expect
HasDecompTest.test_aten_core_operators.expect
HasDecompTest.test_has_decomposition.expect
export
test_export.py
test_pass_infra.py
test_passes.py
test_serialize.py
test_upgrade.py
functorch
test_aotdispatch.py
test_control_flow.py
test_eager_transforms.py
fx
test_fx_split.py
inductor
test_aot_inductor.py
test_cpu_repro.py
test_foreach.py
test_fused_attention.py
test_group_batch_fusion.py
test_inductor_freezing.py
test_mkldnn_pattern_matcher.py
test_pattern_matcher.py
test_perf.py
test_profiler.py
test_snode_runtime.py
test_torchinductor.py
test_torchinductor_opinfo.py
test_triton_heuristics.py
nn
test_pooling.py
onnx
dynamo
test_dynamo_with_onnxruntime_backend.py
test_exporter_api.py
expect
TestOperators.test_acos.expect
TestOperators.test_add_broadcast.expect
TestOperators.test_add_left_broadcast.expect
TestOperators.test_add_size1_broadcast.expect
TestOperators.test_add_size1_right_broadcast.expect
TestOperators.test_add_size1_singleton_broadcast.expect
TestOperators.test_addconstant.expect
TestOperators.test_addmm.expect
TestOperators.test_arange_dynamic.expect
TestOperators.test_argmax.expect
TestOperators.test_asin.expect
TestOperators.test_at_op.expect
TestOperators.test_atan.expect
TestOperators.test_aten_embedding_1.expect
TestOperators.test_aten_embedding_2.expect
TestOperators.test_avg_pool2d.expect
TestOperators.test_baddbmm.expect
TestOperators.test_basic.expect
TestOperators.test_batchnorm.expect
TestOperators.test_batchnorm_1d.expect
TestOperators.test_batchnorm_noaffine.expect
TestOperators.test_batchnorm_onnx_irv4.expect
TestOperators.test_batchnorm_training.expect
TestOperators.test_bitshift.expect
TestOperators.test_c2_op.expect
TestOperators.test_chunk.expect
TestOperators.test_clip.expect
TestOperators.test_clip_max.expect
TestOperators.test_clip_min.expect
TestOperators.test_concat2.expect
TestOperators.test_conv.expect
TestOperators.test_conv_onnx_irv4.expect
TestOperators.test_conv_onnx_irv4_opset8.expect
TestOperators.test_convtranspose.expect
TestOperators.test_cos.expect
TestOperators.test_cumsum.expect
TestOperators.test_det.expect
TestOperators.test_dict.expect
TestOperators.test_dict_str.expect
TestOperators.test_dim.expect
TestOperators.test_dropout.expect
TestOperators.test_dropout_default.expect
TestOperators.test_dropout_opset12.expect
TestOperators.test_dropout_training.expect
TestOperators.test_dropout_training_opset12.expect
TestOperators.test_dynamic_axes_add.expect
TestOperators.test_dynamic_axes_add_inputs_same_symbolic_shape.expect
TestOperators.test_dynamic_axes_matmul.expect
TestOperators.test_dynamic_axes_reduce_mean.expect
TestOperators.test_dynamic_axes_unchange.expect
TestOperators.test_elu.expect
TestOperators.test_embedding_bags.expect
TestOperators.test_empty_like.expect
TestOperators.test_equal.expect
TestOperators.test_erf.expect
TestOperators.test_exp.expect
TestOperators.test_expand.expect
TestOperators.test_flatten.expect
TestOperators.test_flatten2D.expect
TestOperators.test_fmod.expect
TestOperators.test_frobenius_norm.expect
TestOperators.test_full.expect
TestOperators.test_full_like.expect
TestOperators.test_gather.expect
TestOperators.test_gather_opset11.expect
TestOperators.test_ge.expect
TestOperators.test_gelu.expect
TestOperators.test_gt.expect
TestOperators.test_hardtanh.expect
TestOperators.test_implicit_expand.expect
TestOperators.test_index.expect
TestOperators.test_isnan.expect
TestOperators.test_layer_norm_aten.expect
TestOperators.test_le.expect
TestOperators.test_linear.expect
TestOperators.test_log_sigmoid.expect
TestOperators.test_logsoftmax.expect
TestOperators.test_lstm_none_sequence_lens.expect
TestOperators.test_lt.expect
TestOperators.test_master_opset.expect
TestOperators.test_max.expect
TestOperators.test_maxpool.expect
TestOperators.test_maxpool_dilations.expect
TestOperators.test_maxpool_indices.expect
TestOperators.test_mean.expect
TestOperators.test_mean_dtype.expect
TestOperators.test_meshgrid.expect
TestOperators.test_min.expect
TestOperators.test_mm.expect
TestOperators.test_mul_bool.expect
TestOperators.test_mul_fp_bool.expect
TestOperators.test_narrow.expect
TestOperators.test_ne.expect
TestOperators.test_nonzero.expect
TestOperators.test_norm_p1.expect
TestOperators.test_norm_p2.expect
TestOperators.test_ones_like.expect
TestOperators.test_pad.expect
TestOperators.test_params.expect
TestOperators.test_params_onnx_irv4.expect
TestOperators.test_permute2.expect
TestOperators.test_pixel_shuffle.expect
TestOperators.test_pow.expect
TestOperators.test_prelu.expect
TestOperators.test_prod.expect
TestOperators.test_prod_dtype.expect
TestOperators.test_rand.expect
TestOperators.test_randn.expect
TestOperators.test_reduce_sum_negative_indices.expect
TestOperators.test_reduced_mean.expect
TestOperators.test_reduced_mean_dtype.expect
TestOperators.test_reduced_mean_keepdim.expect
TestOperators.test_reduced_prod.expect
TestOperators.test_reduced_prod_dtype.expect
TestOperators.test_reduced_prod_keepdim.expect
TestOperators.test_reduced_sum.expect
TestOperators.test_reduced_sum_dtype.expect
TestOperators.test_reduced_sum_keepdim.expect
TestOperators.test_reducemax.expect
TestOperators.test_reducemin.expect
TestOperators.test_remainder.expect
TestOperators.test_repeat.expect
TestOperators.test_repeat_dim_overflow.expect
TestOperators.test_round.expect
TestOperators.test_rrelu.expect
TestOperators.test_rsqrt.expect
TestOperators.test_rsub.expect
TestOperators.test_scatter_add.expect
TestOperators.test_scatter_add_opset11.expect
TestOperators.test_scatter_add_opset16.expect
TestOperators.test_selu.expect
TestOperators.test_shape_value_map.expect
TestOperators.test_sign.expect
TestOperators.test_sin.expect
TestOperators.test_slice.expect
TestOperators.test_slice_dynamic.expect
TestOperators.test_softmaxcrossentropy.expect
TestOperators.test_softmaxcrossentropy_3d.expect
TestOperators.test_softmaxcrossentropy_3d_none.expect
TestOperators.test_softmaxcrossentropy_4d.expect
TestOperators.test_softmaxcrossentropy_ignore_index.expect
TestOperators.test_softmaxcrossentropy_weights.expect
TestOperators.test_split.expect
TestOperators.test_split_with_sizes.expect
TestOperators.test_sqrt.expect
TestOperators.test_std.expect
TestOperators.test_sum.expect
TestOperators.test_sum_dtype.expect
TestOperators.test_tan.expect
TestOperators.test_topk.expect
TestOperators.test_topk_smallest_unsorted.expect
TestOperators.test_transpose.expect
TestOperators.test_type_as.expect
TestOperators.test_unfold.expect
TestOperators.test_unique.expect
TestOperators.test_unsqueeze.expect
TestOperators.test_upsample_nearest_scale.expect
TestOperators.test_upsample_nearest_scale_default_scale_factor.expect
TestOperators.test_upsample_nearest_size.expect
TestOperators.test_view.expect
TestOperators.test_view_flatten.expect
TestOperators.test_zeros_like.expect
onnx_test_common.py
test_fx_op_consistency.py
test_fx_to_onnx.py
test_fx_to_onnx_with_onnxruntime.py
test_op_consistency.py
test_pytorch_onnx_no_runtime.py
test_pytorch_onnx_onnxruntime.py
optim
test_optim.py
profiler
test_profiler.py
test_profiler_tree.py
quantization
core
experimental
test_float8.py
test_quantized_op.py
pt2e
test_quantize_pt2e.py
test_quantize_pt2e_fx.py
test_x86inductor_quantizer.py
run_test.py
test_autograd.py
test_binary_ufuncs.py
test_cpp_extensions_jit.py
test_cuda.py
test_custom_ops.py
test_dataloader.py
test_dynamic_shapes.py
test_hub.py
test_matmul_cuda.py
test_meta.py
test_modules.py
test_mps.py
test_nn.py
test_ops.py
test_proxy_tensor.py
test_python_dispatch.py
test_pytree.py
test_serialization.py
test_sparse.py
test_sparse_csr.py
test_sparse_semi_structured.py
test_subclass.py
test_torch.py
test_transformers.py
test_view_ops.py
torch_np
numpy_tests
core
test_getlimits.py
test_indexing.py
test_numeric.py
test_scalarmath.py
lib
test_function_base.py
test_histograms.py
test_nanfunctions.py
test_type_check.py
test_basic.py
third_party
ideep
mkl-dnn.BUILD
nccl
nccl
tools
autograd
derivatives.yaml
pyi
gen_pyi.py
stats
import_test_stats.py
upload_metrics.py
upload_stats_lib.py
upload_test_stat_aggregates.py
test
test_heuristics.py
test_test_selections.py
test_upload_stats_lib.py
testing
target_determination
determinator.py
heuristics
__init__.py
correlated_with_historical_failures.py
edited_by_pr.py
interface.py
previously_failed_in_pr.py
utils.py
test_selections.py
torch
_C
__init__.pyi.in
_distributed_rpc.pyi
_functorch.pyi
_profiler.pyi
__init__.py
_decomp
__init__.py
decompositions.py
_dynamo
allowed_functions.py
backends
onnxrt.py
torchxla.py
config.py
convert_frame.py
eval_frame.py
exc.py
guards.py
mutation_guard.py
output_graph.py
source.py
symbolic_convert.py
utils.py
variables
builder.py
builtin.py
ctx_manager.py
dicts.py
higher_order_ops.py
lists.py
misc.py
tensor.py
torch.py
user_defined.py
_export
__init__.py
db
case.py
examples
constrain_as_size_example.py
constrain_as_value_example.py
exported_program.py
pass_base.py
passes
add_runtime_assertions_for_constraints_pass.py
serde
schema.py
serialize.py
upgrade.py
utils.py
_functorch
aot_autograd.py
partitioners.py
_guards.py
_higher_order_ops
cond.py
out_dtype.py
_inductor
codecache.py
codegen
aot_inductor_interface.cpp
common.py
cpp.py
cpp_prefix.h
triton.py
triton_foreach.py
wrapper.py
compile_fx.py
config.py
cudagraph_trees.py
decomposition.py
freezing.py
fx_passes
binary_folding.py
freezing_patterns.py
fuse_attention.py
group_batch_fusion.py
mkldnn_fusion.py
post_grad.py
pre_grad.py
quantization.py
graph.py
index_propagation.py
ir.py
kernel
conv.py
mm.py
mm_common.py
mm_plus_mm.py
lowering.py
pattern_matcher.py
quantized_lowerings.py
scheduler.py
triton_heuristics.py
virtualized.py
_logging
_internal.py
_meta_registrations.py
_numpy
__init__.py
_binary_ufuncs_impl.py
_funcs_impl.py
_getlimits.py
_ndarray.py
_reductions_impl.py
testing
utils.py
_ops.py
_prims
rng_prims.py
_refs
__init__.py
nn/functional
__init__.py
_subclasses
fake_tensor.py
meta_utils.py
_tensor.py
_torch_docs.py
_utils.py
ao/quantization
__init__.py
fx
prepare.py
pt2e
_propagate_annotation.py
graph_utils.py
prepare.py
qat_utils.py
representation
rewrite.py
utils.py
quantize_pt2e.py
quantizer
quantizer.py
x86_inductor_quantizer.py
xnnpack_quantizer.py
xnnpack_quantizer_utils.py
autograd
profiler.py
csrc
DataLoader.cpp
Device.cpp
Device.h
Dtype.cpp
DynamicTypes.cpp
Generator.cpp
Module.cpp
PyInterpreter.cpp
Size.cpp
Size.h
StorageMethods.cpp
StorageSharing.cpp
Stream.cpp
TypeInfo.cpp
autograd
function.h
function_hook.h
functions
accumulate_grad.cpp
accumulate_grad.h
python_hook.cpp
python_hook.h
python_torch_functions_manual.cpp
python_variable.cpp
python_variable.h
variable.cpp
variable.h
cuda
Graph.cpp
Module.cpp
memory_snapshot.cpp
distributed/c10d
socket.cpp
dynamo
compiled_autograd.h
cpython_defs.c
cpython_defs.h
eval_frame.c
guards.cpp
inductor
aot_inductor_interface.h
aot_inductor_model.h
aot_inductor_model_container.h
jit
codegen/onednn
LlgaTensorImpl.cpp
LlgaTensorImpl.h
graph_helper.cpp
kernel.cpp
operator.h
frontend
schema_type_parser.cpp
serialization
export.cpp
unpickler.cpp
onnx/diagnostics/generated
rules.h
profiler/python
init.cpp
utils
init.cpp
invalid_arguments.cpp
pybind.cpp
python_arg_parser.cpp
python_arg_parser.h
python_compat.h
python_dispatch.cpp
python_strings.h
tensor_flatten.h
tensor_new.cpp
throughput_benchmark.cpp
throughput_benchmark.h
cuda
graphs.py
memory.py
distributed
_functional_collectives.py
_tensor
__init__.py
api.py
debug
__init__.py
device_mesh.py
redistribute.py
checkpoint
_fsspec_filesystem.py
_sharded_tensor_utils.py
filesystem.py
optimizer.py
planner.py
utils.py
distributed_c10d.py
fsdp
_common_utils.py
_runtime_utils.py
flat_param.py
fully_sharded_data_parallel.py
run.py
tensor/parallel
_data_parallel_utils.py
fsdp.py
style.py
utils.py
export
__init__.py
extension.h
fx
experimental
symbolic_shapes.py
graph.py
passes
split_utils.py
proxy.py
traceback.py
hub.py
nn
functional.py
modules
activation.py
loss.py
utils
rnn.py
onnx
__init__.py
_constants.py
_internal
diagnostics
_rules.py
rules.yaml
exporter.py
fx
_pass.py
fx_onnx_interpreter.py
passes
modularization.py
onnxruntime.py
symbolic_opset11.py
utils.py
optim
adam.py
adam.pyi
adamw.py
adamw.pyi
nadam.py
sgd.py
overrides.py
profiler
_memory_profiler.py
profiler.py
sparse
__init__.py
semi_structured.py
testing/_internal
common_device_type.py
common_methods_invocations.py
common_modules.py
common_utils.py
distributed
_tensor
common_dtensor.py
fake_pg.py
inductor_utils.py
opinfo/definitions
special.py
optests
__init__.py
generate_tests.py
utils
_pytree.py
_sympy
functions.py
interp.py
value_ranges.py
_traceback.py
cpp_extension.py
data
_utils
worker.py
dataloader.py
hipify
cuda_to_hip_mappings.py
torchgen
api
python.py
types
types.py
model.py
Loading