strisunshinewentingwang/pytorch

Pull Requests Commits

rohan-varma committed 2 years ago

7cb439d6

Merge remote-tracking branch 'origin/master' into clean_fix

rohan-varma committed 2 years ago

08c412aa

[quant][core][better-engineering] Rename files in quantized/cuda directory to conform with non-quantized countertpart filenames #77431

dzdang committed 2 years ago

a9b68009

Add lazy shape inference for logical boolean ops (#78004)

wonjoolee95 committed 2 years ago

593d66e1

torch/distributed: move WorkerInfo registration into libtorch instead of libtorch_python (#78028)

d4l3k committed 2 years ago

ebba4219

rohan-varma committed 2 years ago

4e04d0e5

[FSDP] Remove unneeded padding logic for optim state dict

awgu committed 2 years ago

8412f209

rohan-varma committed 2 years ago

e1480211

rohan-varma committed 2 years ago

be87fb1d

Add from_blob with storage_offset arg

JacobSzwejbka committed 2 years ago

cdb009c8

ns for fx: remove restriction on nodes with no args and only kwargs

vkuzo committed 2 years ago

53e05ad4

Fix typo in testname (#78258)

malfet committed 2 years ago

70508265

[Profiler] Abstract interface for Python tracer

Taylor Robie committed 2 years ago

e0a071a4

[Profiler] Build call tree in `collection.cpp`

Taylor Robie committed 2 years ago

34d160b1

[XLA hash update] update the pinned xla hash (#78144)

pytorchmergebot committed 2 years ago

9f9e8ff2

ci: Remove verbose windows compilation commands (#78197)

clee2000 committed 2 years ago

7e767729

rohan-varma committed 2 years ago

aa1ebe27

Conversion between SparseBsr and Strided (#78025)

cpuhrsch committed 2 years ago

b9fb940d

[MPS] Lazy initialize allocators (#78227)

malfet committed 2 years ago

2679aa47

[quant][core][improvement][bug fix] Added channel axis bound checking in fused_moving_avg_obs_fake_quant_*

dzdang committed 2 years ago

ba952d83

[quant][core][gpu][improvement] Made plan and run for quantized linear op conform with Conv_v8.cpp

dzdang committed 2 years ago

a98b1a8b

[quant][core][gpu][improvement] Removed linear_output and set output tensors as virtual in quantized cudnn linear op

dzdang committed 2 years ago

b4471148

Pass WITH_BLAS option from environment to CMake (#78037)

Flamefire committed 2 years ago

d5f99581

[quant][core][gpu][improvement] Made plan and run for quantized cudnn conv op conform with Conv_v8.cpp

dzdang committed 2 years ago

589f40e3

Revert "[quant] Add utility function get_fqn_to_example_inputs"

pytorchmergebot committed 2 years ago

87148f2b

[PyTorch] Fix record function inputs_valid_ check (#78002)

louisfeng committed 2 years ago

82cb7210

remove torch.no_grad from sample_inputs (#78076)

kshitij12345 committed 2 years ago

17c1aed2

[quant][core][gpu][improvement] Removed conv_output and set output tensors as virtual in quantized cudnn conv2d op

dzdang committed 2 years ago

bd5ec6c8

[quant] Add utility function get_fqn_to_example_inputs

jerryzh168 committed 2 years ago

50a44fe4

[quant][core][gpu][improvement] Enabled broadcasting multiplication support for requantize_multiplier_tensor in quantized cudnn add, linear, and conv2d ops

dzdang committed 2 years ago

b2917526

Older