Search results

fwd_rng_state show up in the aot_export_joint grpah input

module: aotdispatchumbrella label for AOTAutograd issuesumbrella label for AOTAutograd issues

module: pt2-dispatcherPT2 dispatcher-related issues (e.g., aotdispatch, functionalization, faketensor, custom-op,PT2 dispatcher-related issues (e.g., aotdispatch, functionalization, faketensor, custom-op,

oncall: pt2

triagedThis issue has been looked at a team member, and triaged and prioritized into an appropriate moduleThis issue has been looked at a team member, and triaged and prioritized into an appropriate module

Status: Open.

#164559 In pytorch/pytorch;

· SherlockNoMad opened on Oct 3, 2025

[cpu inductor] [silent incorrectness] <code>permute-randn_like</code> outputs incorrect results with <code>backend='aot_eager_decomp_partition'</code>

module: aotdispatchumbrella label for AOTAutograd issuesumbrella label for AOTAutograd issues

module: pt2-dispatcherPT2 dispatcher-related issues (e.g., aotdispatch, functionalization, faketensor, custom-op,PT2 dispatcher-related issues (e.g., aotdispatch, functionalization, faketensor, custom-op,

module: randomRelated to random number generation in PyTorch (rng generator)Related to random number generation in PyTorch (rng generator)

oncall: pt2

triagedThis issue has been looked at a team member, and triaged and prioritized into an appropriate moduleThis issue has been looked at a team member, and triaged and prioritized into an appropriate module

Status: Open.

#164546 In pytorch/pytorch;

· shaoyuyoung opened on Oct 3, 2025

flex_attention doesn't work when wrapped with inductor backend

intelThis tag is for PR from IntelThis tag is for PR from Intel

module: flex attention

module: higher order operatorstorch.cond and similartorch.cond and similar

module: pt2-dispatcherPT2 dispatcher-related issues (e.g., aotdispatch, functionalization, faketensor, custom-op,PT2 dispatcher-related issues (e.g., aotdispatch, functionalization, faketensor, custom-op,

oncall: pt2

triagedThis issue has been looked at a team member, and triaged and prioritized into an appropriate moduleThis issue has been looked at a team member, and triaged and prioritized into an appropriate module

Status: Open.

#164248 In pytorch/pytorch;

· tugsbayasgalan opened on Sep 30, 2025

Dynamo graph break on flex attention code

module: dynamo

module: flex attention

module: graph breaks

module: higher order operatorstorch.cond and similartorch.cond and similar

module: pt2-dispatcherPT2 dispatcher-related issues (e.g., aotdispatch, functionalization, faketensor, custom-op,PT2 dispatcher-related issues (e.g., aotdispatch, functionalization, faketensor, custom-op,

oncall: pt2

triagedThis issue has been looked at a team member, and triaged and prioritized into an appropriate moduleThis issue has been looked at a team member, and triaged and prioritized into an appropriate module

Status: Open.

#164247 In pytorch/pytorch;

· tugsbayasgalan opened on Sep 30, 2025

Flexattention create mask function return a bool tensor when using score mod

module: flex attention

module: pt2-dispatcherPT2 dispatcher-related issues (e.g., aotdispatch, functionalization, faketensor, custom-op,PT2 dispatcher-related issues (e.g., aotdispatch, functionalization, faketensor, custom-op,

oncall: pt2

triagedThis issue has been looked at a team member, and triaged and prioritized into an appropriate moduleThis issue has been looked at a team member, and triaged and prioritized into an appropriate module

Status: Open.

#164096 In pytorch/pytorch;

· paoxiaode opened on Sep 29, 2025

[Fuzzer][Eager/Compile Divergence] Argument 'sym_size_int_3' of Node 'full_default' was used before it has been defined!

module: aotdispatchumbrella label for AOTAutograd issuesumbrella label for AOTAutograd issues

module: dynamic shapes

module: pt2-dispatcherPT2 dispatcher-related issues (e.g., aotdispatch, functionalization, faketensor, custom-op,PT2 dispatcher-related issues (e.g., aotdispatch, functionalization, faketensor, custom-op,

oncall: pt2

topic: fuzzer

triagedThis issue has been looked at a team member, and triaged and prioritized into an appropriate moduleThis issue has been looked at a team member, and triaged and prioritized into an appropriate module

Status: Open.

#164088 In pytorch/pytorch;

· bobrenjc93 opened on Sep 28, 2025

[Fuzzer][Eager/Compile Divergence] DDE _get_symint_hints(ph_arg.stride()) != real_stride:

module: dynamic shapes

module: pt2-dispatcherPT2 dispatcher-related issues (e.g., aotdispatch, functionalization, faketensor, custom-op,PT2 dispatcher-related issues (e.g., aotdispatch, functionalization, faketensor, custom-op,

oncall: pt2

topic: fuzzer

triagedThis issue has been looked at a team member, and triaged and prioritized into an appropriate moduleThis issue has been looked at a team member, and triaged and prioritized into an appropriate module

Status: Open.

#163894 In pytorch/pytorch;

· bobrenjc93 opened on Sep 25, 2025

torch compile does not handle out_dtype argument in torch.addmm/baddbmm (but succeeds with torch.bmm/mm)

module: fakeTensor

module: pt2-dispatcherPT2 dispatcher-related issues (e.g., aotdispatch, functionalization, faketensor, custom-op,PT2 dispatcher-related issues (e.g., aotdispatch, functionalization, faketensor, custom-op,

oncall: pt2

triagedThis issue has been looked at a team member, and triaged and prioritized into an appropriate moduleThis issue has been looked at a team member, and triaged and prioritized into an appropriate module

Status: Open.

#163880 In pytorch/pytorch;

· ad8e opened on Sep 25, 2025

[Fuzzer][Eager/Compile Divergence] Node full_1 was invalid, but is output

module: pt2-dispatcherPT2 dispatcher-related issues (e.g., aotdispatch, functionalization, faketensor, custom-op,PT2 dispatcher-related issues (e.g., aotdispatch, functionalization, faketensor, custom-op,

oncall: pt2

topic: fuzzer

triagedThis issue has been looked at a team member, and triaged and prioritized into an appropriate moduleThis issue has been looked at a team member, and triaged and prioritized into an appropriate module

Status: Open.

#163877 In pytorch/pytorch;

· bobrenjc93 opened on Sep 25, 2025

compile error with custom softmax triton kernel

module: pt2-dispatcherPT2 dispatcher-related issues (e.g., aotdispatch, functionalization, faketensor, custom-op,PT2 dispatcher-related issues (e.g., aotdispatch, functionalization, faketensor, custom-op,

module: user tritonrelated to ability to directly torch.compile triton kernelsrelated to ability to directly torch.compile triton kernels

oncall: pt2

triagedThis issue has been looked at a team member, and triaged and prioritized into an appropriate moduleThis issue has been looked at a team member, and triaged and prioritized into an appropriate module

Status: Open.

#163811 In pytorch/pytorch;

· mayank31398 opened on Sep 24, 2025

torch.compile bug because aot autograd trace ignores requires_grad

module: aotdispatchumbrella label for AOTAutograd issuesumbrella label for AOTAutograd issues

module: pt2-dispatcherPT2 dispatcher-related issues (e.g., aotdispatch, functionalization, faketensor, custom-op,PT2 dispatcher-related issues (e.g., aotdispatch, functionalization, faketensor, custom-op,

oncall: pt2

triagedThis issue has been looked at a team member, and triaged and prioritized into an appropriate moduleThis issue has been looked at a team member, and triaged and prioritized into an appropriate module

Status: Open.

#163716 In pytorch/pytorch;

· yanboliang opened on Sep 24, 2025

Allow double in native_functions.yaml as a schema type

module: cpp-extensionsRelated to torch.utils.cpp_extensionRelated to torch.utils.cpp_extension

module: dispatchDispatchStub, Type, void pointer table, c10 dispatchDispatchStub, Type, void pointer table, c10 dispatch

module: libraryRelated to torch.library (for registering ops from Python)Related to torch.library (for registering ops from Python)

module: pt2-dispatcherPT2 dispatcher-related issues (e.g., aotdispatch, functionalization, faketensor, custom-op,PT2 dispatcher-related issues (e.g., aotdispatch, functionalization, faketensor, custom-op,

oncall: pt2

triagedThis issue has been looked at a team member, and triaged and prioritized into an appropriate moduleThis issue has been looked at a team member, and triaged and prioritized into an appropriate module

Status: Open.

#163659 In pytorch/pytorch;

· janeyx99 opened on Sep 23, 2025