|
How to share CUcontext with other application?
|
|
0
|
657
|
June 12, 2023
|
|
OpenReg Dispatching Structured Ops
|
|
0
|
512
|
May 28, 2023
|
|
How to find out which operators are supported by HIP
|
|
0
|
554
|
May 25, 2023
|
|
Faketensor error when add new backend for pytorch
|
|
1
|
571
|
May 11, 2023
|
|
Improve the extension with `PrivateUse1` for custom device
|
|
8
|
1419
|
April 17, 2023
|
|
Is there a place for storing custom data within PyTorch Tensor
|
|
8
|
1493
|
March 23, 2023
|
|
Set of ops for a backend to register
|
|
10
|
2225
|
March 10, 2023
|
|
A small MPS debugging story
|
|
3
|
1553
|
March 9, 2023
|
|
Why is mps_copy_ not registered to copy_stub
|
|
0
|
435
|
March 8, 2023
|
|
Can backend compilers modify guards for torch Dynamo frame
|
|
4
|
674
|
February 28, 2023
|
|
Keeping PyTorch's Ops Maintainable: The Jiterator
|
|
7
|
1722
|
February 27, 2023
|
|
Private use opencl device
|
|
7
|
1822
|
November 11, 2022
|
|
How to keep up with updates of operator signatures
|
|
6
|
1053
|
November 4, 2022
|
|
What is the reason for using old ABI on Linux?
|
|
3
|
841
|
October 30, 2022
|
|
Lazy Tensor Core
|
|
20
|
7288
|
July 12, 2022
|
|
Memory operations on a custom backend
|
|
4
|
1119
|
July 5, 2022
|
|
PyTorch and TensorFloat32
|
|
5
|
10841
|
June 28, 2022
|
|
More In-Depth Details of Floating Point Precision
|
|
0
|
3394
|
June 21, 2022
|
|
Automatic out-of-tree backend loading
|
|
1
|
767
|
December 13, 2021
|
|
Debugging back-propogation results
|
|
4
|
812
|
November 18, 2021
|
|
OpenCL Backend: Broadcast/Reduce Ops
|
|
3
|
1429
|
November 5, 2021
|
|
Aten::abs_out called with an undefined 'out' tensor
|
|
1
|
1008
|
November 4, 2021
|
|
Aten::mul.out receives tensors from mixed devices
|
|
2
|
1208
|
October 16, 2021
|
|
Asynchronous Execution and Memory Management
|
|
3
|
2140
|
October 11, 2021
|
|
Slides from Structured Kernel presentation
|
|
4
|
1544
|
April 8, 2021
|