-
Notifications
You must be signed in to change notification settings - Fork 31k
All issues
Issue creation is restricted in this repository
- #198239 · atalman opened
on Sep 22, 2026 4
Issues
is:issue state:open
is:issue state:open
Search results
sort/topk/cummax and other (values, indices) ops silently return wrong results when both out= tensors overlap (int64 input)
bot-triagedThis is a label only to be used by the auto triage botThis is a label only to be used by the auto triage botmodule: correctness (silent)issue that returns an incorrect result silentlyissue that returns an incorrect result silentlymodule: partial aliasingRelated to correctly supporting overlapping storages in operationsRelated to correctly supporting overlapping storages in operationsStatus: Open.#199020 In pytorch/pytorch;[dynamo] Enum with a member named "name" crashes torch.compile
bot-triagedThis is a label only to be used by the auto triage botThis is a label only to be used by the auto triage bottriagedThis 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 moduleStatus: Open.#199019 In pytorch/pytorch;[Inductor] Compiled softshrink turns NaN into zero
bot-triagedThis is a label only to be used by the auto triage botThis is a label only to be used by the auto triage botmodule: NaNs and InfsProblems related to NaN and Inf handling in floating pointProblems related to NaN and Inf handling in floating pointStatus: Open.#199017 In pytorch/pytorch;DISABLED test_copy_transpose_tiled_small_case_at_cuda_float16 (__main__.TestTorchDeviceTypeCUDA)
module: flaky-testsProblem is a flaky test in CIProblem is a flaky test in CImodule: rocmAMD GPU support for PytorchAMD GPU support for Pytorchmodule: testsIssues related to tests (not the torch.testing module)Issues related to tests (not the torch.testing module)skippedDenotes a (flaky) test currently skipped in CI.Denotes a (flaky) test currently skipped in CI.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 moduleStatus: Open.#199016 In pytorch/pytorch;Inductor doesn't work with clang++ 21 (most likely PCH failure)
bot-triagedThis is a label only to be used by the auto triage botThis is a label only to be used by the auto triage botmodule: macosMac OS related issuesMac OS related issuestriagedThis 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 moduleStatus: Open.#199014 In pytorch/pytorch;Optimizer.load_state_dict is quadratic in the number of parameters
bot-triagedThis is a label only to be used by the auto triage botThis is a label only to be used by the auto triage botenhancementNot as big of a feature, but technically not a bug. Should be easy to fixNot as big of a feature, but technically not a bug. Should be easy to fixmodule: optimizerRelated to torch.optimRelated to torch.optimmodule: performanceIssues related to performance, either of kernel code or framework glueIssues related to performance, either of kernel code or framework gluetriagedThis 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 moduleStatus: Open.#199004 In pytorch/pytorch;DISABLED test_sdpa_rewriter_stacked_layers_with_mask_gpu (__main__.SDPAPatternRewriterGpuDynamicTests)
bot-triagedThis is a label only to be used by the auto triage botThis is a label only to be used by the auto triage botmodule: xpuIntel XPU related issuesIntel XPU related issuesskippedDenotes a (flaky) test currently skipped in CI.Denotes a (flaky) test currently skipped in CI.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 moduleStatus: Open.#198998 In pytorch/pytorch;DISABLED test_sdpa_rewriter_stacked_layers_with_mask_gpu (__main__.SDPAPatternRewriterGpuTests)
bot-triagedThis is a label only to be used by the auto triage botThis is a label only to be used by the auto triage botmodule: xpuIntel XPU related issuesIntel XPU related issuesskippedDenotes a (flaky) test currently skipped in CI.Denotes a (flaky) test currently skipped in CI.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 moduleStatus: Open.#198997 In pytorch/pytorch;Tensor.requires_grad_ typing is incorrectly defined in __init__.pyi
bot-triagedThis is a label only to be used by the auto triage botThis is a label only to be used by the auto triage botmodule: typingRelated to mypy type annotationsRelated to mypy type annotationstriagedThis 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 moduleStatus: Open.#198996 In pytorch/pytorch;[Inductor] soft_margin_loss returns wrong dtype for mixed-dtype input and target
bot-triagedThis is a label only to be used by the auto triage botThis is a label only to be used by the auto triage botStatus: Open.#198994 In pytorch/pytorch;[accelerator] Should can_device_access_peer be exposed under torch.accelerator
bot-triagedThis is a label only to be used by the auto triage botThis is a label only to be used by the auto triage botfunction requestA request for a new function or the addition of new arguments/modes to an existing function.A request for a new function or the addition of new arguments/modes to an existing function.module: acceleratorIssues related to the shared accelerator APIIssues related to the shared accelerator APItriagedThis 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 moduleStatus: Open.#198993 In pytorch/pytorch;Long queue for g5 runnners
ci: sevcritical failure affecting PyTorch CIcritical failure affecting PyTorch CItriagedThis 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 moduleStatus: Open.#198991 In pytorch/pytorch;