About the compiler category
|
|
0
|
1515
|
January 22, 2021
|
Torch.export functionalization changed?
|
|
2
|
50
|
July 24, 2025
|
Export_memory_timeline doesn't work with torch.profile
|
|
0
|
16
|
July 23, 2025
|
Error during build setup, has anyone experienced this?
|
|
1
|
39
|
July 20, 2025
|
Extern declaration of the entity XXX is treated as a static definition
|
|
0
|
36
|
July 10, 2025
|
Does dynamo trigger real kernel execution?
|
|
4
|
109
|
July 1, 2025
|
Torch.compile support for Python 3.13 completed
|
|
2
|
1718
|
June 27, 2025
|
[question] how dynamo or aot-autograd optimize slice operation?
|
|
1
|
53
|
June 27, 2025
|
Detect shared weights across subgraphs in torch.compile
|
|
2
|
94
|
June 23, 2025
|
TorchFuser: A Plug-and-Play MLIR-Based Compiler and Optimized Runtime Integration
|
|
4
|
326
|
June 3, 2025
|
Functionalization in PyTorch: Everything You Wanted To Know
|
|
8
|
6710
|
May 28, 2025
|
Inconsistent precision between PyTorch's built-in backends for the same device
|
|
0
|
55
|
May 27, 2025
|
Questions about handling non-scalar kwargs in pattern matcher and kwargs capture in replacements
|
|
2
|
127
|
May 21, 2025
|
Conditional Decompositions
|
|
0
|
70
|
April 30, 2025
|
Understanding CUDAGraph Trees
|
|
6
|
1239
|
April 15, 2025
|
Empty tensor with SymInt size
|
|
1
|
107
|
April 15, 2025
|
Profiling torch.compile
|
|
0
|
117
|
April 10, 2025
|
Inductor Triton Custom Op
|
|
6
|
1470
|
March 25, 2025
|
How to prevent ops to be decomposed in custom compile backend
|
|
0
|
97
|
March 24, 2025
|
AOT module decompositions
|
|
1
|
376
|
March 13, 2025
|
A new strategy for automatic custom operators functionalization
|
|
1
|
297
|
February 8, 2025
|
Generated AOTInductor C shim header files have unexpectedly changed
|
|
1
|
73
|
February 7, 2025
|
No CPU backend in triton
|
|
4
|
662
|
January 20, 2025
|
Inductor Passes
|
|
0
|
258
|
January 13, 2025
|
What’s preventing PyTorch from being competitive with Llamafile?
|
|
8
|
444
|
December 10, 2024
|
"Fused compiled autograd bwd + optimizer graph" - status update?
|
|
4
|
375
|
November 21, 2024
|
FMAs (and softmax (and floating point)) considered harmful
|
|
2
|
728
|
November 21, 2024
|
CUDAGraphs in Pytorch 2.0
|
|
6
|
5212
|
November 20, 2024
|
Where do the 2000+ PyTorch operators come from?: More than you wanted to know
|
|
13
|
14136
|
November 15, 2024
|
Compiled Optimizer w/ LR Scheduler Now Supported
|
|
3
|
556
|
November 13, 2024
|