strisunshinewentingwang/pytorch

Pull Requests Commits

Add support for lowering info during serialize_module, and add padding/partial to it (#5810)

jfix71 committed 3 years ago

6cc8cc6e

cat_shape_check: Fixes dimension in the error message for CUDA cat shape check and removes unnecessary offending index information (#64556)

mabdullahsoyturk committed 3 years ago

d43fb75a

Enable the on-demand performance PR testing to run on a specified TB branch (#64701)

xuzhao9 committed 3 years ago

2c243ed1

.github: Remove add_annotations workflow (#64449)

seemethere committed 3 years ago

51703391

[Dist/CI] Remove dist from target determinator (#64721)

rohan-varma committed 3 years ago

9797a32f

fix acc topk's handling of the case when dim=0, fix tests as well (#64727)

emad committed 3 years ago

46c886e8

Fix a shadowed variable (#64695)

r-barnes committed 3 years ago

3d3ff4a9

Added more version comparison operations (#63848)

nivedwho committed 3 years ago

8deaa476

Reverts cat and stack warning when out= is not the expected shape (#64714)

Mike Ruberry committed 3 years ago

cfa6162e

To add SequentialLR to PyTorch Core Schedulers (#64037)

iramazanli committed 3 years ago

2b41bf40

[pytorch] Make qlinear weight packing thread safe (#63804)

John Shen committed 3 years ago

c3203efe

`torch.lu_solve`: forward AD support (#64646)

nikitaved committed 3 years ago

dc535466

[nnc] Handled cast in index expression during inlining (#64716)

navahgar committed 3 years ago

b7c86365

[nnc] Updated indices during broadcast to use int64_t (#64627)

navahgar committed 3 years ago

652a8bf7

Revert D30745921: [DDP] Fix when buffers are reassigned in module

H-Huang committed 3 years ago

459653a0

Revert D30745961: [DDP] Remove self.modules_params

H-Huang committed 3 years ago

5bc53ac5

Revert D30745960: [DDP] Remove SPMD from self.modules_buffers

H-Huang committed 3 years ago

f1aaf8af

[JIT] Add gradient check in constants (#64613)

Elias Ellison committed 3 years ago

3bf93d76

Filter out _disabled_torch_function_impl from handle_torch_function (#64689)

ezyang committed 3 years ago

d4b10168

To add Rectified Adam Description to Documentation (#63772)

iramazanli committed 3 years ago

239366c9

[doc][hackathon] To add AdamW Optimizer to the documentation (#63252)

iramazanli committed 3 years ago

5b21f172

To add Adamax algorithm to documentation (#63903)

iramazanli committed 3 years ago

39ce801d

[AutoAccept][Codemod][FBSourceClangFormatLinter] Daily `arc lint --take CLANGFORMAT`

CodemodService FBSourceClangFormatLinterBot committed 3 years ago

15c21fa4

Fix lop1p lowering bug (#64724)

Yinghai Lu committed 3 years ago

233e3e5b

Migrate uses of THCReduceApplyUtils to cuda_utils::BlockReduce (#64713)

peterbell10 committed 3 years ago

d0b207e6

[DDP] Remove SPMD from self.modules_buffers (#64474)

rohan-varma committed 3 years ago

15532595

[DDP] Remove self.modules_params (#64473)

rohan-varma committed 3 years ago

8c095102

[DDP] Fix when buffers are reassigned in module (#64472)

rohan-varma committed 3 years ago

d59ecc02

[PyTorch] Fix MobileDebugInfo vector copy (#64030)

swolchok committed 3 years ago

b6544ef8

[PyTorch] move from input ivalues in ByteCodeDeserializer (#64029)

swolchok committed 3 years ago

0d0d2f2a

Newer Older