strisunshinewentingwang/pytorch

Pull Requests Commits

Update ROCm PyTorch persons of interest (#55206)

jithunnair-amd committed 3 years ago

726fd26b

Remove `_fork_processes` from common_distributed.py (#63711)

pritamdamania committed 3 years ago

d6133b2f

Made FuncTorchBatched decompose CompositeImplicitAutograd (#63616)

Chillee committed 3 years ago

2289a12f

BatchNorm autodiff re-enabled (#57321)

jjsjann123 committed 3 years ago

e926f75b

Revert D30360382: [nnc] Support thread level parallelism in fused kernels

bertmaher committed 3 years ago

37d60c08

Revert D30417127: Remove flag to toggle CPU fusion in the presence of parallelism

bertmaher committed 3 years ago

76da46cc

[sharded_tensor] add readonly tensor properties (#63679)

wanchaol committed 3 years ago

8871ff29

[Static Runtime] Implement out variant for fb::quantized_linear (#63635)

Hao Lu committed 3 years ago

b2a601ff

NNAPI: Support const values in binary ops

Akshit Khurana committed 3 years ago

2d58f3f5

Migrate thnn_conv2d from THC to ATen (#63428)

peterbell10 committed 3 years ago

b4f5809d

Extend _sharded_tensor constructor to support other ops like torch.ones (#63378)

bowangbj committed 3 years ago

3ee1f81d

[clang-tidy] Enable more folders (#63380)

driazati committed 3 years ago

7c0f5b9a

enable increment build for build_libtorch (#63074)

mszhanyi committed 3 years ago

e0fe5699

[Doc] Deprecation notice for only_inputs argument (#63631)

eliphatfs committed 3 years ago

efe01c59

Remove breakpad from docker image (#63598)

driazati committed 3 years ago

bcf8e2f5

add BFloat16 operators on CPU: range, sinh, cosh, frexp, nan_to_num (#61826)

jiayisunx committed 3 years ago

da0820e5

empty caching allocator before test_avg_pool2d large subtest (#63528)

jeffdaily committed 3 years ago

a8de0d83

Include iostream in ProcessGroupMPI.cpp (#63656)

malfet committed 3 years ago

b008bb44

[easy]Unbreak caffe2benchmarking build (#63655)

swolchok committed 3 years ago

07e41cf2

[ONNX] Suppport torch.dot and torch.nn.utils.spectral_norm (#62596) (#62765)

BowenBao committed 3 years ago

1dd648f1

[ONNX] Update repeat_interleave for dynamic repeats (#59979) (#62764)

BowenBao committed 3 years ago

db0771b0

[ONNX] Fix an issue that optimizations might adjust graph inputs unexpectedly. (#61280) (#62763)

BowenBao committed 3 years ago

87602549

[ONNX] Fix controlflow shape inference with contrib op (#60707) (#62762)

BowenBao committed 3 years ago

a65d1ae7

Revert D30417370: [nnc] Enable CPU fusion

albanD committed 3 years ago

125e2d02

[8/N] Remove c10d/ddp fork tests. (#63454)

pritamdamania committed 3 years ago

2d671ca4

Revert D30426527: Adding DataLoader2 class as future replacement of DataLoader

albanD committed 3 years ago

71da1144

Add `BinaryUfuncOpInfo` and broadcasting tests (#61964)

pmeier committed 3 years ago

70a3210e

[nnc] Enable CPU fusion (#63545)

bertmaher committed 3 years ago

b9fc656c

Remove flag to toggle CPU fusion in the presence of parallelism (#63514)

bertmaher committed 3 years ago

6600bc96

[nnc] Support thread level parallelism in fused kernels (#63386)

bertmaher committed 3 years ago

d6d86efb

Newer Older