Skip to content

Issues: microsoft/DirectML

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

216 Open 195 Closed
216 Open 195 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

About "pad" tuple of the arguments of the torch.nn.functional.pad function with torch_directml
#687 opened Feb 17, 2025 by suryodasuke
1
Multiplication of a float tensor and a bool tensor produces a bool tensor on PyTorch
#686 opened Feb 2, 2025 by kazssym
Undefined behavior of DML_OPERATOR_GATHER operator on Qualcomm Snapdragon X GPU and NPU
#685 opened Jan 25, 2025 by SID37
1
Blue screen when running AI Dev Gallery model with shared memory
#683 opened Jan 17, 2025 by hansmbakker
c# I need to run the program on NPU (OnnxRuntime + DirectML + NPU)，
#682 opened Jan 14, 2025 by Gusha-nye
Resize input image (ID3D12Resource) to model size using directx
#681 opened Jan 11, 2025 by bvnp43
1
GPU memory is no correct : (/job:localhost/replica:0/task:0/device:GPU:0 with 82826 MB memory) my GPU has 24gb !!!
#680 opened Jan 10, 2025 by Nal44
How to run phi3 on NPU via OnnxRuntime+DirectML
#679 opened Jan 7, 2025 by Gusha-nye
5
aten::native_group_norm_backward is not currently supported on the DML backend and will fall back to run on the CPU
#678 opened Dec 30, 2024 by Inokinoki
aten::_thnn_fused_lstm_cell not supported on the DML backend and not implemented on CPU
#677 opened Dec 25, 2024 by cinco-de-mayonnaise
1
How can DML_OPERATOR_MULTIHEAD_ATTENTION map to a single metacommand?
#676 opened Dec 17, 2024 by JianxiaoLuIntel
The operator 'aten::lerp.Scalar_out' is not currently supported on the DML backend and will fall back to run on the CPU. This may have performance implications.
#675 opened Dec 8, 2024 by lovelyallen
1
hit build error on vs2022
#674 opened Dec 2, 2024 by ychding11
DirectML Allocates Excessive Memory Exceeding the Capacity of Radeon RX 6700 XT GPU
#673 opened Dec 2, 2024 by Hedredo
2
Unknown error -2005270521 was caught when testing torch-directml resnet50 demo
#672 opened Nov 30, 2024 by Basicname
'aten::linalg_inv_ex.inverse' AND 'aten::_linalg_svd.U' is not currently supported on the DML backend
#671 opened Nov 27, 2024 by shenth222
Using Intel NPU on DirectML_ESRGAN
#670 opened Nov 26, 2024 by bonihaniboni
Error with PyTorch backpropagation
#668 opened Nov 16, 2024 by alterrion-git
1
Another DxDispatch issue with QCOM Hexagon NPU on Windows (CompileOperator)
#666 opened Nov 14, 2024 by fobrs
6
'aten::count_nonzero.dim_intlist' is not currently supported on the dml backend and will fall back to run on the cpu'
#665 opened Nov 14, 2024 by Alkimical
Example to run yolo model on NPU
#664 opened Nov 7, 2024 by fobrs
2
Does torch-directml support Conv3D?
#663 opened Nov 6, 2024 by AdvancedHe
DxDispatch issue with QCOM NPU on Windows
#662 opened Oct 29, 2024 by mram0509
1
Using directML to inference accelerate onnxruntime, a crash occurred
#657 opened Oct 20, 2024 by yunhaolsh
Unable to distribute embedded python with torch-directml
#656 opened Oct 17, 2024 by bcw222
ProTip! Follow long discussions with comments:>50.