..
_awaits
_C
Allow new_full's fill_value argument type to be complex ( #91345 )
2023-03-21 12:34:00 +00:00
_C_flatbuffer
_decomp
Improve size mismatch error messaging referencing mat/vet sizes ( #96863 )
2023-03-17 21:07:48 +00:00
_dispatch
_dynamo
[dynamo] handle dim in size kwargs ( #96992 ) ( #97098 )
2023-03-22 14:19:59 +00:00
_export
[aot autograd] merge all outputs of funtionalization analysis into single metadata ( #95991 )
2023-03-08 16:22:54 +00:00
_functorch
Changed logging in aotautograd a little ( #97289 )
2023-03-22 09:33:30 +00:00
_inductor
inductor(cpu): support mkldnn packed linear to improve bfloat16 performance ( #96954 )
2023-03-22 12:25:59 +00:00
_lazy
_logging
Improve TORCH_LOGS settings error msg ( #97264 )
2023-03-22 13:26:53 +00:00
_prims
Bump black version to 23.1.0 ( #96578 )
2023-03-15 06:27:59 +00:00
_prims_common
Add support for nonzero, some improvements to reduce guards ( #95387 )
2023-02-24 00:27:45 +00:00
_refs
Allow new_full's fill_value argument type to be complex ( #91345 )
2023-03-21 12:34:00 +00:00
_subclasses
Don't run fallback if symbolic sizes in fake tensor ( #97148 )
2023-03-21 02:23:44 +00:00
amp
Error only if autocast actually enabled ( #96097 )
2023-03-21 03:13:13 +00:00
ao
Init quantization backend config for inductor ( #96476 )
2023-03-22 07:56:56 +00:00
autograd
Deprecate gradcheck check_sparse_nnz argument as duplicate of masked argument ( #97187 )
2023-03-22 14:11:03 +00:00
backends
DOC: Various typo fixes ( #97095 )
2023-03-20 20:46:04 +00:00
contrib
cpu
csrc
Test and fix guard fail message in CompileProfiler ( #97055 )
2023-03-22 02:17:57 +00:00
cuda
Change 1D Tensor of 1 element to 0D Tensor ( #96994 )
2023-03-21 18:24:19 +00:00
distributed
[PTD][Checkpoint] Add checkpointing support for DTensor submesh ( #96802 )
2023-03-21 08:17:17 +00:00
distributions
Fix gumbel cdf ( #91698 )
2023-03-07 23:04:47 +00:00
fft
func
[functorch] linearize ( #94173 )
2023-02-09 15:45:08 +00:00
futures
fx
DCE inference graphs too ( #97275 )
2023-03-22 01:02:21 +00:00
jit
Add location information for assertions in torch.jit.annotations.try_ann_to_type ( #96423 )
2023-03-11 21:49:13 +00:00
legacy
lib
Simplify cmake code ( #91546 )
2023-02-08 01:05:19 +00:00
linalg
masked
std/var: support floating point correction value ( #94073 )
2023-02-23 05:50:45 +00:00
monitor
mps
[MPS] Enable Memory Leak Detection for test_mps.py ( #94646 )
2023-02-13 17:56:24 +00:00
multiprocessing
FIX make sure we import the correct object from multiprocessing ( #81862 )
2023-03-21 14:48:17 +00:00
nested
nn
Update parallel_apply.py for assertion error when len(modules) != len(inputs) ( #94671 )
2023-03-21 17:46:23 +00:00
onnx
[ONNX] 'Transform' as base class for passes ( #95935 )
2023-03-21 03:31:22 +00:00
optim
Change 1D Tensor of 1 element to 0D Tensor ( #96994 )
2023-03-21 18:24:19 +00:00
package
Bump black version to 23.1.0 ( #96578 )
2023-03-15 06:27:59 +00:00
profiler
[BE] Remove unnecessary dict comprehensions ( #97116 )
2023-03-20 00:56:57 +00:00
quantization
AO migration: replace torch internal callsites ( #94170 )
2023-02-07 02:32:23 +00:00
signal
sparse
bsr_dense_mm Triton kernel: fix out kwarg ( #96648 )
2023-03-14 18:01:22 +00:00
special
testing
Deprecate gradcheck check_sparse_nnz argument as duplicate of masked argument ( #97187 )
2023-03-22 14:11:03 +00:00
utils
[draft for discussion] add per-dispatch key modes ( #97052 )
2023-03-21 23:45:45 +00:00
__config__.py
__future__.py
__init__.py
component-level configurable logging for dynamo, inductor, aot ( #94858 )
2023-03-18 04:17:31 +00:00
_appdirs.py
_classes.py
[BE] [2/3] Rewrite super() calls in functorch and torch ( #94588 )
2023-02-10 21:16:33 +00:00
_deploy.py
_guards.py
Extend aot autograd dedup guards to params, stop using positions ( #96774 )
2023-03-21 05:59:33 +00:00
_jit_internal.py
Fix usages of contextmanager without finally ( #96170 )
2023-03-08 20:59:27 +00:00
_linalg_utils.py
_lobpcg.py
Bump black version to 23.1.0 ( #96578 )
2023-03-15 06:27:59 +00:00
_lowrank.py
_meta_registrations.py
[SDPA] Remove the chunk_grad from mem-eff attention ( #96880 )
2023-03-17 21:28:25 +00:00
_namedtensor_internals.py
_ops.py
[draft for discussion] add per-dispatch key modes ( #97052 )
2023-03-21 23:45:45 +00:00
_python_dispatcher.py
_sources.py
[BE] [2/3] Rewrite super() calls in functorch and torch ( #94588 )
2023-02-10 21:16:33 +00:00
_storage_docs.py
_tensor_docs.py
Add masked_grad kw argument to to_dense ( #96095 )
2023-03-16 21:38:11 +00:00
_tensor_str.py
[BE] Remove dependency on six and future ( #94709 )
2023-02-14 09:14:14 +00:00
_tensor.py
Add HPU to compatible shallow copy list and remove lazy HPU changes ( #94673 )
2023-02-14 17:15:25 +00:00
_torch_docs.py
docs: Match open bracket with close bracket in unsqueeze ( #95215 )
2023-02-24 03:56:59 +00:00
_utils_internal.py
_utils.py
Bump black version to 23.1.0 ( #96578 )
2023-03-15 06:27:59 +00:00
_VF.py
[BE] [2/3] Rewrite super() calls in functorch and torch ( #94588 )
2023-02-10 21:16:33 +00:00
_vmap_internals.py
_weights_only_unpickler.py
Add float to list of allowed ops ( #94910 )
2023-02-15 23:13:21 +00:00
abi-check.cpp
CMakeLists.txt
fix some tiny code issues ( #95757 )
2023-03-01 23:27:32 +00:00
custom_class_detail.h
custom_class.h
More fixes and improved clang-tidy checkers ( #93213 )
2023-02-01 14:44:17 +00:00
extension.h
functional.py
Require DOCTEST_SHOW environ to run plt.show ( #96522 )
2023-03-10 21:47:20 +00:00
hub.py
[BE]: pyupgrade Python to 3.8 - imports and object inheritance only ( #94308 )
2023-02-07 21:10:56 +00:00
library.h
Fix dispatching issue of the new device type. ( #97273 )
2023-03-21 23:23:06 +00:00
library.py
overrides.py
Refactor NT offsets metadata to be a Tensor ( #96909 )
2023-03-21 18:51:35 +00:00
py.typed
quasirandom.py
[BE]: pyupgrade Python to 3.8 - imports and object inheritance only ( #94308 )
2023-02-07 21:10:56 +00:00
random.py
[MPS] Add Python Module Bindings for the MPS backend ( #94417 )
2023-02-12 21:22:30 +00:00
README.txt
return_types.py
script.h
serialization.py
Fix usages of contextmanager without finally ( #96170 )
2023-03-08 20:59:27 +00:00
storage.py
Make share_memory_ call thread safe within itself. ( #96664 )
2023-03-14 19:27:01 +00:00
torch_version.py
types.py
Allow new_full's fill_value argument type to be complex ( #91345 )
2023-03-21 12:34:00 +00:00
5537792307