Jerry Zhang a73c6a45b6 [reland][quant][graphmode][fx] Enable fuse handler for sequence of 3 ops (#70006) ... Summary: Pull Request resolved: https://github.com/pytorch/pytorch/pull/70006 reland: fixing some mypy errors that was missed before This PR enables fuse handler for sequence of three ops, and merges all fuse handlers into one TODO: we can also move this to backend_config_dict folder Test Plan: regression fusion test ``` python test/test_quantization.py TestFuseFx ``` Imported from OSS Imported from OSS Reviewed By: supriyar Differential Revision: D33144606 fbshipit-source-id: ca34f282018a0fb4d04c7e35119eaf2d64258e78		2021-12-16 15:04:16 -08:00
..
ao/sparsity	[sparsity] Convert function for sparse kernels without a context manager (#66778)	2021-12-09 02:58:57 -08:00
autograd
backward_compatibility	Revert D33136054: Remove backward ops for miopen convolution	2021-12-16 12:46:02 -08:00
benchmark_utils	Add lint to ensure all test files have headers with ownership info (#66826)	2021-11-03 18:21:49 -07:00
bottleneck_test
cpp	[jit][edge] Remove usage of shared_ptr<mobile::Code>. (#68037)	2021-12-16 13:11:46 -08:00
cpp_api_parity
cpp_extensions	Resubmit #67161 (#67735)	2021-11-04 09:59:30 -07:00
custom_backend	[PyTorch] Adopt IValue::toTupleRef() where obvious (#65505)	2021-11-02 10:22:18 -07:00
custom_operator
distributed	Provide functionality to write custom ShardedTensor ops. (#69874)	2021-12-16 12:40:13 -08:00
distributions	Add formulas for distributions (#69690)	2021-12-14 23:35:07 -08:00
error_messages
expect	Fixed type checking errors in node.py (#68124)	2021-12-03 12:03:49 -08:00
fx	[const_fold] Fix call_module const folding (#68614)	2021-11-18 20:56:06 -08:00
fx2trt	Revert D33024528: [quant][fx][graphmode] Add support for conv add pattern in backend_config_dict	2021-12-15 05:45:29 -08:00
fx_acc	[fx2trt] Add torch.nn.function.pad support for fx2trt (#67498)	2021-11-03 10:21:08 -07:00
jit	Add test operator in upgrader entry (#69427)	2021-12-15 00:40:05 -08:00
jit_hooks
mobile	[Operator Versioning][Edge] Codegen upgrader_mobile.cpp (#69194)	2021-12-16 10:29:35 -08:00
onnx	[ONNX] Add BFloat16 type support when export to ONNX (#66788)	2021-12-14 12:23:32 -08:00
package	[package] fix torchscript classes in package (#68028)	2021-11-16 10:01:40 -08:00
quantization	[reland][quant][graphmode][fx] Enable fuse handler for sequence of 3 ops (#70006)	2021-12-16 15:04:16 -08:00
scripts
test_img
typing
delete.py
HowToWriteTestsUsingFileCheck.md
linear.py
run_test.py	Revert D33004315: Support torch.equal for ShardedTensor.	2021-12-15 14:14:06 -08:00
simulate_nccl_errors.py
test_ao_sparsity.py	[sparsity] Fix and enable the pruning tests (#66411)	2021-11-22 15:28:12 -08:00
test_autocast.py
test_autograd.py	Add forward AD layout check for storage numel (#68631)	2021-12-14 04:34:25 -08:00
test_binary_ufuncs.py	Enable cpu scalar arguments for jiterator (#69861)	2021-12-16 10:58:59 -08:00
test_bundled_images.py	Add ownership to more edge tests (#67859)	2021-11-05 11:01:16 -07:00
test_bundled_inputs.py	Add lint to ensure all test files have headers with ownership info (#66826)	2021-11-03 18:21:49 -07:00
test_complex.py
test_cpp_api_parity.py
test_cpp_extensions_aot.py	Resubmit #67161 (#67735)	2021-11-04 09:59:30 -07:00
test_cpp_extensions_jit.py	Remove remaining THC code (#69039)	2021-12-08 12:18:08 -08:00
test_cuda.py	Fixes mem_get_info when querying on a device other than the current device (#69640)	2021-12-08 23:04:30 -08:00
test_cuda_primary_ctx.py
test_dataloader.py	[DataPipe] Control shuffle settings from DataLoader2 (#65756)	2021-12-14 07:35:26 -08:00
test_datapipe.py	[DataPipe] Control shuffle settings from DataLoader2 (#65756)	2021-12-14 07:35:26 -08:00
test_deploy.py
test_determination.py
test_dispatch.py
test_foreach.py	Fix device type / dtype handling for parametrized test names (#65217)	2021-11-29 19:02:23 -08:00
test_function_schema.py
test_functional_autograd_benchmark.py
test_functional_optim.py
test_functionalization.py	functionalization: update is_aliased() logic (#68881)	2021-12-02 09:19:12 -08:00
test_futures.py
test_fx.py	OpInfos for: normal, bernoulli, multinomial (#66358)	2021-12-14 06:59:38 -08:00
test_fx_experimental.py	OpInfos for: normal, bernoulli, multinomial (#66358)	2021-12-14 06:59:38 -08:00
test_gen_backend_stubs.py	Revert D32498569: allow external backend codegen to toggle whether to generate out= and inplace kernels	2021-12-14 15:27:24 -08:00
test_import_stats.py
test_indexing.py	Fixes CUDA vs CPU consistency for index_put_ when accumulating (part 2) (#67189)	2021-11-08 17:56:43 -08:00
test_jit.py	[JIT] Enable freezing for sparse COO tensors (#69614)	2021-12-14 15:43:50 -08:00
test_jit_autocast.py	[JIT] additional support for CallMethod with autocasting (#67925)	2021-11-08 14:37:09 -08:00
test_jit_cuda_fuser.py	Nvfuser code bump 12 5 (#69964)	2021-12-16 08:28:54 -08:00
test_jit_disabled.py
test_jit_fuser.py	skip test_jit_legacy (#68129)	2021-11-10 23:08:32 -08:00
test_jit_fuser_legacy.py
test_jit_fuser_te.py	[TensorExpr] Supress TracerWarnings in test_unsupported in test_jit_fuser_te.py. (#68757)	2021-11-30 00:06:36 -08:00
test_jit_legacy.py
test_jit_profiling.py
test_jit_simple.py
test_jit_string.py
test_kernel_launch_checks.py
test_license.py
test_linalg.py	[Linalg] Add a runtime switch to let pytorch prefer a backend impl in linalg functions on GPU (#67980)	2021-12-03 19:06:30 -08:00
test_logging.py
test_masked.py	Strided masked var. (#68738)	2021-12-01 19:19:37 -08:00
test_metal.py
test_mkldnn.py	Avoid the view for mkldnn case in 1D convolution (#68166)	2021-11-15 11:56:45 -08:00
test_mobile_optimizer.py
test_model_dump.py	Add ownership to more edge tests (#67859)	2021-11-05 11:01:16 -07:00
test_module_init.py	[quant][embedding qat] eager mode QAT for Embeddings (#66429)	2021-11-18 05:57:11 -08:00
test_modules.py	[nn] mha : no-batch-dim support (python) (#67176)	2021-12-14 13:21:21 -08:00
test_multiprocessing.py
test_multiprocessing_spawn.py
test_namedtensor.py
test_namedtuple_return_api.py	expose return_types in Python (#66614)	2021-12-06 09:05:29 -08:00
test_native_functions.py
test_nn.py	Add support for masked_softmax when softmax_elements > 1024 & corresponding unit tests (#69924)	2021-12-15 16:44:15 -08:00
test_nnapi.py	Add ownership to more edge tests (#67859)	2021-11-05 11:01:16 -07:00
test_numba_integration.py
test_numpy_interop.py
test_openmp.py
test_ops.py	Add testing for forward over reverse gradgrad (#69740)	2021-12-14 23:35:10 -08:00
test_optim.py	Adds a maximize flag to Adam (#68164)	2021-12-13 05:53:53 -08:00
test_overrides.py	Add linalg.solve_triangular (#63568)	2021-11-22 12:41:06 -08:00
test_package.py
test_profiler.py	record the datapipe for each pieces of Dataset (#67613)	2021-12-01 10:29:06 -08:00
test_pruning_op.py
test_public_bindings.py
test_python_dispatch.py	add python dispatch test back to CI and fix typo in test (#69565)	2021-12-08 08:44:49 -08:00
test_pytree.py
test_quantization.py	[quant][graphmode][fx] Fork subgraph_rewriter from torch.fx to quantization (#68228)	2021-11-24 10:49:05 -08:00
test_reductions.py	Updated searchsorted functionality (#66818)	2021-11-05 12:13:47 -07:00
test_segment_reductions.py
test_serialization.py	Avoid dtype mismatch error in torch.save if storages are unallocated (#68787)	2021-11-24 09:51:29 -08:00
test_set_default_mobile_cpu_allocator.py	Add ownership to more edge tests (#67859)	2021-11-05 11:01:16 -07:00
test_shape_ops.py
test_show_pickle.py	Add ownership to more edge tests (#67859)	2021-11-05 11:01:16 -07:00
test_sort_and_select.py	Implement topk with sort for some cases (#68632)	2021-11-19 17:18:20 -08:00
test_sparse.py	OpInfo: Allow sample_inputs_func to be any iterable (#69256)	2021-12-09 08:37:26 -08:00
test_sparse_csr.py	Sparse CSR CUDA: Add block sparse support for torch.triangular_solve (#68709)	2021-12-16 13:03:42 -08:00
test_spectral_ops.py
test_stateless.py
test_static_runtime.py	[static runtime][dper] multi_env tests for static runtime: selective enable (#67467)	2021-11-18 01:04:12 -08:00
test_tensor_creation_ops.py	Add meta support to tensor range factories (#67032)	2021-11-05 15:36:29 -07:00
test_tensorboard.py
test_tensorexpr.py
test_tensorexpr_pybind.py	[tensorexpr] check for index out of bounds in ir_eval (#68858)	2021-12-16 09:27:45 -08:00
test_testing.py	Fix device type / dtype handling for parametrized test names (#65217)	2021-11-29 19:02:23 -08:00
test_throughput_benchmark.py
test_torch.py	Porting index_add to structured kernels, add an out variant (#65993)	2021-12-14 11:57:13 -08:00
test_type_hints.py
test_type_info.py
test_type_promotion.py
test_typing.py
test_unary_ufuncs.py	The Jiterator (#69439)	2021-12-06 07:32:48 -08:00
test_utils.py	Add support for C++ frontend wrapper on Linux (#69094)	2021-12-02 16:47:00 -08:00
test_view_ops.py	Add forward AD support for as_strided (#68629)	2021-12-14 04:33:05 -08:00
test_vmap.py	Add OpInfo test and fix a couple cases (#66294)	2021-11-19 14:31:03 -08:00
test_vulkan.py
test_xnnpack_integration.py	Add ownership to more edge tests (#67859)	2021-11-05 11:01:16 -07:00