ErjiaGuan 5158a6b41a Foward fix sharding bug for DL (#79124) ... This PR solves a bug introduced by #79041 `torch.utils.data.graph_settings.apply_sharding` changes the datapipe in-place and returns `None` It would resolve the Error in TorchData. See: https://github.com/pytorch/data/actions/runs/2461030312 Pull Request resolved: https://github.com/pytorch/pytorch/pull/79124 Approved by: https://github.com/VitalyFedyunin		2022-06-08 16:16:58 +00:00
..
backcompat
benchmark	Convert type comments to annotations in caffe2/torch/util (#72667)	2022-02-11 20:50:20 +00:00
bottleneck
data	Foward fix sharding bug for DL (#79124)	2022-06-08 16:16:58 +00:00
hipify	Sparse BSR: Enable addmm, addmv, triangular_solve for BSR layout (#77255)	2022-05-12 08:31:44 +00:00
jit	Create __init__.py (#78629)	2022-06-03 18:14:21 +00:00
model_dump	Reland "Make debug_pkl smaller by only emitting unique traces." (#73368)	2022-04-18 22:34:21 +00:00
tensorboard	black formatting for utils/tensorboard (#76396)	2022-04-28 00:21:58 +00:00
__init__.py
_cpp_extension_versioner.py
_crash_handler.py
_freeze.py
_mode_utils.py	enable with semantics	2022-06-01 21:14:45 +00:00
_python_dispatch.py	add better error message for class method	2022-06-06 13:31:32 +00:00
_pytree.py
_zip.py
bundled_inputs.py	[lint] upgrade mypy to latest version	2022-05-03 20:51:34 +00:00
checkpoint.py	Fix issue with _checkpoint_without_reentrant	2022-05-05 17:37:31 +00:00
collect_env.py	tools: Ensure compat for collect_env with python 3.5	2022-06-06 21:32:57 +00:00
cpp_extension.py	Allow relocatable device code linking in pytorch CUDA extensions (#78225)	2022-06-02 21:35:56 +00:00
dlpack.py
file_baton.py
hooks.py
mkldnn.py	Enable fp32/bf16 PRelu forward and backward in MkldnnCPU path (#60427)	2022-05-10 17:29:11 +00:00
mobile_optimizer.py
model_zoo.py
show_pickle.py	[lint] upgrade mypy to latest version	2022-05-03 20:51:34 +00:00
throughput_benchmark.py