|
Inconsistent precision between PyTorch's built-in backends for the same device
|
|
0
|
116
|
May 27, 2025
|
|
Questions about handling non-scalar kwargs in pattern matcher and kwargs capture in replacements
|
|
2
|
209
|
May 21, 2025
|
|
Conditional Decompositions
|
|
0
|
125
|
April 30, 2025
|
|
Understanding CUDAGraph Trees
|
|
6
|
1951
|
April 15, 2025
|
|
Empty tensor with SymInt size
|
|
1
|
203
|
April 15, 2025
|
|
Profiling torch.compile
|
|
0
|
277
|
April 10, 2025
|
|
Inductor Triton Custom Op
|
|
6
|
2041
|
March 25, 2025
|
|
How to prevent ops to be decomposed in custom compile backend
|
|
0
|
147
|
March 24, 2025
|
|
AOT module decompositions
|
|
1
|
447
|
March 13, 2025
|
|
Generated AOTInductor C shim header files have unexpectedly changed
|
|
1
|
149
|
February 7, 2025
|
|
No CPU backend in triton
|
|
4
|
1100
|
January 20, 2025
|
|
What’s preventing PyTorch from being competitive with Llamafile?
|
|
8
|
865
|
December 10, 2024
|
|
"Fused compiled autograd bwd + optimizer graph" - status update?
|
|
4
|
506
|
November 21, 2024
|
|
FMAs (and softmax (and floating point)) considered harmful
|
|
2
|
952
|
November 21, 2024
|
|
CUDAGraphs in Pytorch 2.0
|
|
6
|
5877
|
November 20, 2024
|
|
Where do the 2000+ PyTorch operators come from?: More than you wanted to know
|
|
13
|
15324
|
November 15, 2024
|
|
Compiled Optimizer w/ LR Scheduler Now Supported
|
|
3
|
704
|
November 13, 2024
|
|
Understanding dynamic shapes and guards and when it does/does not cause graph breaks
|
|
1
|
527
|
November 7, 2024
|
|
What's the difference between `next_variable()` and `reconstruct()` in `IteratorVariable`
|
|
2
|
117
|
October 26, 2024
|
|
Support for _set with other mutations in graph
|
|
2
|
195
|
October 18, 2024
|
|
Is it possible to disable inlining of custom module for torch.compile?
|
|
1
|
345
|
October 11, 2024
|
|
Impact of multithreading and local caching on torch.compile
|
|
3
|
1188
|
September 27, 2024
|
|
TorchInductor Update 9: Harden Vectorization Support and Enhance Loop Optimizations in TorchInductor CPP Backend
|
|
0
|
712
|
September 4, 2024
|
|
TorchInductor Update 8: Max-autotune Support on CPU with GEMM Template
|
|
0
|
717
|
September 4, 2024
|
|
PyTorch Runtime Error with Compiled Autograd
|
|
1
|
431
|
August 31, 2024
|
|
Pytorch to Triton for Non-GPU Devices
|
|
7
|
2018
|
August 30, 2024
|
|
Difference between the graph break reasons: `Dynamic control flow is not supported at the moment.` and `generic_jump TensorVariable()`
|
|
0
|
407
|
August 30, 2024
|
|
Defining the Core ATen Opset
|
|
12
|
6485
|
August 21, 2024
|
|
Why core aten IR doesn’t contain scalar_tensor overload version of some ops, like bitwise-like ops, remainder and so on?
|
|
0
|
69
|
August 21, 2024
|
|
How to Access Triton Kernels from TorchInductor when running on CPU?
|
|
1
|
1101
|
August 12, 2024
|