strisunshinewentingwang/pytorch

Pull Requests Commits

[Quant][Inductor] Enable the lowering of quantized maxpool2d (#105906)

leslie-fang-intel committed 1 year ago

9319dd1c

[Quant][PT2E] Enable X86InductorQuantizer single quantizable op(maxpool2d) (#105639)

leslie-fang-intel committed 1 year ago

70ca18f8

Add torch.sparse.as_sparse_gradcheck decorator of gradcheck that allows gradcheck input function to receive and return sparse tensors (#107150)

pearu committed 1 year ago

c5ad44be

Support torch.sparse_mask on strided input with sparse CSR, CSC, BSR, and BSC mask. (#107777)

pearu committed 1 year ago

e4b38b9c

Add optional is_coalesced argument to sparse coo tensor factory function. (#107638)

pearu committed 1 year ago

fe3309b4

[DeviceMesh] Expose init_device_mesh (#107969)

wz337 committed 1 year ago

781b7ebe

[ONNX] Return input itself for non-fp inputs and support decimals for aten::round op (#107920)

CYuxian committed 1 year ago

35f4bb9a

Minor fixs to make torchbench runable on torch/xla (#107919)

JackCaoG committed 1 year ago

ed8f2128

[reland][inductor] make thread order consistent with loop order (#107902)

shunting314 committed 1 year ago

95cacb7f

[export] Serialize getattr nodes (#107924)

angelayi committed 1 year ago

4e9d7f87

Disable Constraint constructor (#107918)

tugsbayasgalan committed 1 year ago

27afb1c6

[dynamo] Treat monkey patched .forward as dynamic (#107104)

jansel committed 1 year ago

f877d0a4

[quant][pt2e] Fix annotation for conv no bias case (#107971)

andrewor14 committed 1 year ago

240bdbea

[ONNX] Remove API reference for TorchScript export diagnostics (#107979)

BowenBao committed 1 year ago

25d98a3e

Add runtime assertions for prim values (#107939)

tugsbayasgalan committed 1 year ago

52eb773e

[quant][pt2e] Enable testing for reference quant model representations (#107474)

jerryzh168 committed 1 year ago

f92f69db

Revert "[quant][pt2e][xnnpack_quantizer] Add support for mul and mul_relu (#107930)"

pytorchmergebot committed 1 year ago

8d44b0f5

add channel last 3d support for maxpool3d on CPU (#97775)

CaoE committed 1 year ago

32679963

[ONNX] Support constant tensors in FakeMode exporting (#107836)

titaiwangms committed 1 year ago

ee171465

Bias overflow fix mem eff bias (#107968)

drisspg committed 1 year ago

42d60d01

[quant][pt2e][xnnpack_quantizer] Add support for mul and mul_relu (#107930)

jerryzh168 committed 1 year ago

1d1739dc

Revert "Handle 2D blocking with foreach (#107840)"

pytorchmergebot committed 1 year ago

d35d7de6

[RFC] Change --standalone to bind to a random port (#107734)

kunalb committed 1 year ago

af229ecd

[TP][2D][EZ] Fix Error in FSDP 2D test (#107975)

fduwjj committed 1 year ago

7ef13b18

Make openxla and opexla_eval backend show up in list_backends (#107905)

JackCaoG committed 1 year ago

08e49fe9

[inductor] WeakDep should not prevent dead node elimination (#107813)

peterbell10 committed 1 year ago

6c0ce03b

AOTInductor: error: ‘c10::Dispatcher’ has not been declared for CPU model (#107935)

hl475 committed 1 year ago

71045f48

[Quant][Inductor] Enable quantization conv_binary(add/add_relu) pattern fusion inside inductor (#105456)

leslie-fang-intel committed 1 year ago

1374974d

inductor: support masked load for cpu path (#107670)

XiaobingSuper committed 1 year ago

d2105a86

Handle 2D blocking with foreach (#107840)

mlazos committed 1 year ago

f87ffe47

Newer Older