| Age | Commit message (Expand) | Author | Files | Lines |
|---|
| 2019-02-14 | Speed-up adaptive average pooling for the common case of size=1 output (#17011) | ngimel | 1 | -4/+4 |
| 2019-02-14 | maskrcnn & bert AD coverage part 1 (#16689) | Ailing Zhang | 2 | -112/+11 |
| 2019-02-11 | Don't keep unnecessary saved_inputs alive (#16583) | Adam Paszke | 1 | -7/+68 |
| 2019-02-11 | Enforce same input tensor storage in VariableType functions (#16305) | Will Feng | 1 | -1/+96 |
| 2019-02-11 | optionally zero infinite losses in CTCLoss (#16199) | Thomas Viehmann | 1 | -4/+4 |
| 2019-02-07 | Remove undefined tensor in jit script (#16379) | Wanchao Liang | 1 | -3/+11 |
| 2019-02-05 | Warn when tracing legacy constructors | David Riazati | 1 | -0/+5 |
| 2019-02-05 | Rename IntList to IntArrayRef. (#16751) | Edward Yang | 13 | -169/+170 |
| 2019-02-05 | logsumexp for multiple dimensions (#16475) | Brennan Vincent | 2 | -4/+4 |
| 2019-02-01 | Expose backend extensions to python | Roy Li | 1 | -4/+1 |
| 2019-01-30 | Include ATen/core/functional.h directly instead of torch/csrc/utils/functiona... | Mikhail Zolotukhin | 2 | -5/+13 |
| 2019-01-30 | Fix the flake8 linter | Lu Fang | 1 | -1/+1 |
| 2019-01-29 | create type hint stub files for module torch (#12500) | Thomas Viehmann | 2 | -16/+55 |
| 2019-01-28 | Support Tensor alias annotations for native_functions.yaml (#16239) | Christian Puhrsch | 1 | -1/+1 |
| 2019-01-27 | Fix slogdet sign requiring grad when input requires grad (#16337) | SsnL | 2 | -5/+5 |
| 2019-01-26 | Trace fork and join calls | James Reed | 2 | -2/+2 |
| 2019-01-24 | Add thread-local guard: at::AutoNonVariableTypeMode (#15939) | Will Feng | 1 | -6/+36 |
| 2019-01-24 | Move THCCachingAllocator to c10_cuda. (#16119) | Edward Yang | 1 | -1/+1 |
| 2019-01-24 | Remove unnecessary includes and headers from THCCachingAllocator, move to at:... | Edward Yang | 1 | -1/+1 |
| 2019-01-22 | Revert D13540278: [pytorch][PR] Unhide unique from C++, make unique partially... | Wanchao Liang | 2 | -3/+3 |
| 2019-01-22 | Return namedtuples from torch.* function with multiple return arguments for C... | Xiang Gao | 3 | -10/+65 |
| 2019-01-21 | Unhide unique from C++, make unique partially scriptable (#15256) | Xiang Gao | 2 | -3/+3 |
| 2019-01-18 | add back NNPACK in PyTorch (#15924) | Thomas Viehmann | 1 | -0/+6 |
| 2019-01-18 | Port legacy any(*) to ATen | Shen Li | 1 | -3/+8 |
| 2019-01-17 | Move all Stream and Event Python implementation to C++ (#15937) | Shen Li | 1 | -0/+1 |
| 2019-01-16 | Moving torch.norm to ATen using TensorIterator (#15414) | jiej | 2 | -4/+22 |
| 2019-01-16 | Port the backend of FractionalMaxPool3d from TH to ATen (#15575) | Chandler Zuo | 1 | -0/+7 |
| 2019-01-16 | Port legacy all(*) to ATen (#15540) | Shen Li | 1 | -0/+9 |
| 2019-01-14 | `var` for multiple dimensions (#15892) | Brennan Vincent | 1 | -1/+1 |
| 2019-01-09 | Batched upper triangular, lower triangular (#15257) | vishwakftw | 1 | -10/+3 |
| 2019-01-03 | Add mkldnn conv double backward (#15686) | Ailing Zhang | 1 | -0/+3 |
| 2018-12-21 | Direct FBGEMM integraton into ATen (#13777) | James Reed | 1 | -0/+1 |
| 2018-12-19 | Remove python_default_init from ATen and use Optional (#15234) | Wanchao Liang | 3 | -15/+13 |
| 2018-12-19 | Rename potrs to cholesky_solve (#15334) | vishwakftw | 1 | -4/+4 |
| 2018-12-19 | Optional ScalarType support for native functions & JIT (#15154) | Tugrul Ates | 1 | -1/+0 |
| 2018-12-17 | [TensorIterator fixing mean to output correct result for half precisi… (#14... | Jie | 1 | -2/+11 |
| 2018-12-17 | Port nn fold and unfold to c++ | Roy Li | 1 | -0/+6 |
| 2018-12-17 | Bicubic interpolation for nn.functional.interpolate (#9849) | David Riazati | 1 | -0/+6 |
| 2018-12-13 | Fix derivative for mvlgamma (#15049) | vishwakftw | 1 | -2/+2 |
| 2018-12-12 | Implement torch.tril_indices and torch.triu_indices (#12653) (#14904) | Shen Li | 1 | -1/+3 |
| 2018-12-12 | Kill Type.storage. (#15075) | Gregory Chanan | 1 | -2/+0 |
| 2018-12-07 | Implement `std` for multiple dimensions on CPU devices. (#14535) | Brennan Vincent | 2 | -11/+16 |
| 2018-12-07 | Fix include paths for TensorOptions | Sebastian Messmer | 1 | -1/+1 |
| 2018-12-06 | gradcheck (#14596) | Wei Yang | 2 | -0/+9 |
| 2018-12-06 | Move TensorOptions, DefaultTensorOptions to c10 | Sebastian Messmer | 1 | -2/+2 |
| 2018-12-04 | Use .to to convert new tensors in new_tensor (#14097) | Thomas Viehmann | 1 | -6/+16 |
| 2018-12-04 | Rename _local_scalar to item() (#13676) | Peter Goldsborough | 1 | -1/+1 |
| 2018-12-04 | Back out "Move TensorOptions, DefaultTensorOptions and OptionsGuard to c10" (... | Sebastian Messmer | 1 | -2/+2 |
| 2018-12-04 | Back out "Fix include paths for TensorOptions, DefaultTensorOptions, OptionsG... | Sebastian Messmer | 1 | -1/+1 |
| 2018-12-03 | Fix include paths for TensorOptions, DefaultTensorOptions, OptionsGuard | Sebastian Messmer | 1 | -1/+1 |
