Skip to content

Issues: pytorch/pytorch

[v.2.5.0] Release Tracker
#135522 opened Sep 9, 2024 by kit1980
Open 48
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

13,957 Open 31,446 Closed
13,957 Open 31,446 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

DISABLED test_graph_scaling_fused_optimizers_SGD_cuda_float32 (__main__.TestCudaOptimsCUDA) module: flaky-tests Problem is a flaky test in CI module: unknown We do not know who is responsible for this feature, bug, or test case. skipped Denotes a (flaky) test currently skipped in CI.
#137113 opened Oct 1, 2024 by pytorch-bot bot
1
Something like mark_unbacked but only does size oblivious module: dynamic shapes oncall: pt2
#137100 opened Oct 1, 2024 by ezyang
[CI] Multiple tests fail with Host and device pointer dont match with cudaHostRegister and are being disabled high priority module: ci Related to continuous integration module: cuda Related to torch.cuda, and CUDA support in general
#137098 opened Oct 1, 2024 by ptrblck
Expressions involving Min/Max don't simplify with value ranges information module: dynamic shapes oncall: pt2
#137096 opened Oct 1, 2024 by ezyang
Use SymInt instead of sympy.Expr uniformly in Inductor module: dynamic shapes module: inductor oncall: pt2
#137093 opened Oct 1, 2024 by ezyang
Select parameters and buffers by pattern (using fnmatch or re)
#137089 opened Oct 1, 2024 by mulcyber
Weirdly strided input and mark_unbacked don't play well together module: dynamic shapes oncall: pt2
#137087 opened Oct 1, 2024 by ezyang
1
conv2d boundaries
#137086 opened Oct 1, 2024 by kercos
DISABLED test_graph_scaling_fused_optimizers_Adam_cuda_float32 (__main__.TestCudaOptimsCUDA) module: cuda Related to torch.cuda, and CUDA support in general module: flaky-tests Problem is a flaky test in CI skipped Denotes a (flaky) test currently skipped in CI. triaged This issue has been looked at a team member, and triaged and prioritized into an appropriate module
#137083 opened Oct 1, 2024 by pytorch-bot bot
2
torch._dynamo.config.cache_size_limit behaviour with DDP oncall: pt2
#137081 opened Oct 1, 2024 by bhack
Discrepancy between torch.nn.functional.linear and manual computation with bias under torch.autocast
#137080 opened Oct 1, 2024 by TheoBoyer
Missing librt.so.1, libdl.so.2, libz.so.1 and libpthread.so.0 in PyTorch Source Build (aarch64) module: arm Related to ARM architectures builds of PyTorch. Includes Apple M1 module: build Build system issues needs reproduction Someone else needs to try reproducing the issue given the instructions. No action needed from user triaged This issue has been looked at a team member, and triaged and prioritized into an appropriate module
#137078 opened Oct 1, 2024 by vishwascm
DISABLED test_torchvision_transforms_functional_tensor_resize_non_abi_compatible_cuda (__main__.AOTInductorTestNonABICompatibleCuda) module: flaky-tests Problem is a flaky test in CI module: unknown We do not know who is responsible for this feature, bug, or test case. skipped Denotes a (flaky) test currently skipped in CI.
#137071 opened Oct 1, 2024 by pytorch-bot bot
2
UserWarning: Graph break due to unsupported builtin time.time oncall: pt2
#137068 opened Oct 1, 2024 by drtonyr
DISABLED test_gelu_cpu (__main__.CpuTests) module: flaky-tests Problem is a flaky test in CI module: inductor oncall: pt2 skipped Denotes a (flaky) test currently skipped in CI. triaged This issue has been looked at a team member, and triaged and prioritized into an appropriate module
#137067 opened Oct 1, 2024 by pytorch-bot bot
2
DISABLED test_graph_scaling_fused_optimizers_AdamW_cuda_float32 (__main__.TestCudaOptimsCUDA) module: cuda Related to torch.cuda, and CUDA support in general module: flaky-tests Problem is a flaky test in CI skipped Denotes a (flaky) test currently skipped in CI. triaged This issue has been looked at a team member, and triaged and prioritized into an appropriate module
#137066 opened Oct 1, 2024 by pytorch-bot bot
2
[export] int(x.item()) fails only in strict=False export-triaged This tag is used to tag issues that have been looked by PT2 Export team and determined the next step module: dynamic shapes oncall: export oncall: pt2
#137062 opened Oct 1, 2024 by angelayi
1
[torch.compile] torch.vmap adds constant guard to in_dims that the input mapped over module: dynamic shapes module: dynamo module: functorch Pertaining to torch.func or pytorch/functorch module: vmap oncall: pt2 triaged This issue has been looked at a team member, and triaged and prioritized into an appropriate module
#137061 opened Sep 30, 2024 by yanboliang
@yanboliang
Inductor perform worse with as_strided vs split_with_sizes + subscripts module: inductor module: pt2-dispatcher PT2 dispatcher-related issues (e.g., aotdispatch, functionalization, faketensor, custom-op, module: reinplacing inductor reinplacing, re-inplacing, auto-functionalization, auto functionalization, custom op oncall: pt2 triaged This issue has been looked at a team member, and triaged and prioritized into an appropriate module vllm-compile
#137057 opened Sep 30, 2024 by laithsakka
2
Namespace error when using torch::unravel_index to implement a custom function in cuda. module: numpy Related to numpy support, and also numpy compatibility of our operators triaged This issue has been looked at a team member, and triaged and prioritized into an appropriate module
#137045 opened Sep 30, 2024 by BarakeelFanseuKamhoua
[inductor] requires_stride_order doesn't work with unbacked symints module: custom-operators custom operators, custom ops, custom-operators, custom-ops module: dynamic shapes module: inductor module: pt2-dispatcher PT2 dispatcher-related issues (e.g., aotdispatch, functionalization, faketensor, custom-op, oncall: pt2 triaged This issue has been looked at a team member, and triaged and prioritized into an appropriate module
#137039 opened Sep 30, 2024 by zou3519
@zou3519
1
amp.custom_fwd has incomplete support for library.custom_op high priority module: custom-operators custom operators, custom ops, custom-operators, custom-ops module: pt2-dispatcher PT2 dispatcher-related issues (e.g., aotdispatch, functionalization, faketensor, custom-op, oncall: pt2 triaged This issue has been looked at a team member, and triaged and prioritized into an appropriate module
#137033 opened Sep 30, 2024 by andravin
3
DISABLED test_byte_tensor_assignment (__main__.TestAdvancedIndexing) module: flaky-tests Problem is a flaky test in CI module: macos Mac OS related issues module: mps Related to Apple Metal Performance Shaders framework skipped Denotes a (flaky) test currently skipped in CI. triaged This issue has been looked at a team member, and triaged and prioritized into an appropriate module
#137028 opened Sep 30, 2024 by pytorch-bot bot
3
DISABLED test_open_device_registration (__main__.ExtensionBackendTests) module: flaky-tests Problem is a flaky test in CI module: inductor oncall: pt2 skipped Denotes a (flaky) test currently skipped in CI. triaged This issue has been looked at a team member, and triaged and prioritized into an appropriate module
#137027 opened Sep 30, 2024 by pytorch-bot bot
1
[user triton] error out with export/AOTI if dynamic shape is specialized at tl.constexpr export-triaged This tag is used to tag issues that have been looked by PT2 Export team and determined the next step module: aotinductor aot inductor module: dynamic shapes module: user triton related to ability to directly torch.compile triton kernels oncall: export oncall: pt2
#137024 opened Sep 30, 2024 by davidberard98
@pianpwk
1
ProTip! Type g p on any issue or pull request to go back to the pull request listing page.