About the torch.compile category
|
|
0
|
882
|
January 9, 2023
|
Unable to Utilize GPUs with PyTorch on p2.xlarge EC2 Instances
|
|
1
|
31
|
April 26, 2024
|
Serving Torch_TersorRT converted model with Triton
|
|
0
|
13
|
April 25, 2024
|
Slow convolutions in triton
|
|
0
|
22
|
April 24, 2024
|
Torch.compile generated output files understanding
|
|
0
|
24
|
April 24, 2024
|
Le: "b8[64, 2048, 7, 7]" = torch.ops.aten.le.Scalar(relu_48, 0); relu_48 = None
|
|
1
|
75
|
April 24, 2024
|
Export Multiple Functions of a Pytorch Module
|
|
8
|
294
|
April 24, 2024
|
Any specific reason for chosing the default batch sizes for the torch dynamo benchmark suite
|
|
1
|
37
|
April 22, 2024
|
Can toch.cond be used recursively?
|
|
2
|
51
|
April 22, 2024
|
Error when backpropagating through a compiled PyTorch module multiple times
|
|
1
|
39
|
April 21, 2024
|
Generate Triton kernels for CPU
|
|
3
|
91
|
April 18, 2024
|
Is possible export the model on cpu and run it gpu?
|
|
4
|
74
|
April 17, 2024
|
Compile and deepcopy in the context of early stopping
|
|
0
|
46
|
April 16, 2024
|
Obscure error message when trying to export a compiled function
|
|
0
|
38
|
April 15, 2024
|
Torch.compile when /home is a read only filesystem
|
|
11
|
249
|
April 14, 2024
|
Torch.compile cache_size_limit best practice
|
|
1
|
63
|
April 12, 2024
|
Export and save problem(torch-tensorrt)
|
|
0
|
47
|
April 11, 2024
|
Compile function that uses constant tensor
|
|
1
|
89
|
April 10, 2024
|
How to achieve Torch-MLIR compatibility with Dynamo backend?
|
|
1
|
70
|
April 9, 2024
|
Is it possible to define a custom back-end wrapped with aot_autograd which does not use fake tensors?
|
|
0
|
41
|
April 9, 2024
|
The difference between `torch.ops.aten.addmm.default` and `torch.ops.aten.linear.default`
|
|
0
|
53
|
April 8, 2024
|
[dynamo] [onnx] Models exported with torch.onnx.dynamo_export show worse performance during inference
|
|
0
|
72
|
April 8, 2024
|
Return handle from compiled function from C++ to be used by backend
|
|
1
|
257
|
April 4, 2024
|
Unique node name across graph re-compilations and graph breaks
|
|
0
|
68
|
April 3, 2024
|
Why am I getting segfault when loading an AOT compiled model twice?
|
|
1
|
64
|
April 3, 2024
|
Speedup with max_autotune even though all the triton mm kernels are slower
|
|
0
|
66
|
April 2, 2024
|
Convolution speedup (slowdown) with torch.compile
|
|
4
|
70
|
April 2, 2024
|
Getting RuntimeError While Loading Model Weights
|
|
6
|
133
|
April 2, 2024
|
Memory Footprint of Eager Mode vs Torch Compiled (Default, with CUDA Graph, and CUDA Graph Dynamic)
|
|
2
|
147
|
April 2, 2024
|
Conda CMAKE CXX Compiler error while compiling Pytorch
|
|
0
|
97
|
March 31, 2024
|