|
About the torch._dynamo category
|
|
0
|
654
|
December 6, 2022
|
|
Torch.compile + vmap + jacfwd raises TorchRuntimeError on regular python code but not via eval()
|
|
3
|
116
|
May 21, 2026
|
|
Let HOF (torch.cond, torch.while_loop) skip compilation of input functions if needed
|
|
0
|
51
|
December 17, 2025
|
|
Backend Compiler Graph Break
|
|
0
|
107
|
October 30, 2025
|
|
About dynamo.disable
|
|
0
|
348
|
October 29, 2025
|
|
In Dynamo+AOTAutograd, why run Faketensor through the code multiple times?
|
|
0
|
100
|
September 15, 2025
|
|
Better understanding why AOTAutograd decomposes `fused_rms_norm_backward` for CUDA, but not for Meta tensors
|
|
0
|
98
|
September 15, 2025
|
|
Is there any way to save multiple graphs from same model without redundantly saving their state dicts?
|
|
2
|
135
|
July 19, 2025
|
|
Disabling guards generation using dynamo based export
|
|
1
|
202
|
June 30, 2025
|
|
Issues with PyTorch while_loop operator when exporting the torch model to ExecuTorch
|
|
1
|
211
|
June 19, 2025
|
|
How to customize leaf node in dynamo trace?
|
|
2
|
694
|
May 21, 2025
|
|
[PyTorch 2.7.0] Custom privateuse1 FakeTensor add + float scalar triggers AttributeError: 'float' object has no attribute 'item_memo'
|
|
0
|
348
|
May 19, 2025
|
|
torch._dynamo.exc.Unsupported: call_method NNModuleVariable() _sa_block [TensorVariable(), LazyVariableTracker(), LazyVariableTracker()] {}
|
|
1
|
629
|
April 29, 2025
|
|
Resetting cache in benchmark
|
|
4
|
2338
|
April 23, 2025
|
|
How does torch dynamo set custom eval frame callback?
|
|
1
|
176
|
April 16, 2025
|
|
How to make TorchDynamoc decompose torch.nn.functional.scaled_dot_product_attention?
|
|
1
|
182
|
February 27, 2025
|
|
Mapping between TorchDynamo compiled functions and FX GraphModules
|
|
2
|
173
|
February 27, 2025
|
|
Dynamo.explain() output
|
|
0
|
204
|
February 13, 2025
|
|
Does dynamo trigger real kernel execution?
|
|
3
|
285
|
February 8, 2025
|
|
Support for torch.equal when exporting with Dynamo
|
|
3
|
250
|
February 7, 2025
|
|
PyTorch 2.5.1, torch.compile error
|
|
2
|
721
|
February 4, 2025
|
|
The difference between `torch.ops.aten.addmm.default` and `torch.ops.aten.linear.default`
|
|
2
|
1046
|
February 3, 2025
|
|
Workaround for unsupported return of multiple tensors for torch.cond in a model intended for torch.onnx.export(dynamo=true,...)
|
|
1
|
174
|
February 3, 2025
|
|
Decomposition to Aten IR
|
|
6
|
1359
|
January 31, 2025
|
|
Does warming up the torch.compile necessarily trigger all cases?
|
|
2
|
395
|
January 18, 2025
|
|
Graph breaks or No graph breaks in torchdynamo
|
|
4
|
3815
|
January 14, 2025
|
|
What is the uplimit of dynamo graph cache?
|
|
2
|
368
|
January 10, 2025
|
|
Compiling a model that uses sdp_kernel to enable the backends does not work
|
|
4
|
499
|
December 18, 2024
|
|
Onnx export with dynamo using torch.cond for dynamic models
|
|
0
|
198
|
December 16, 2024
|
|
How to disable ___check_obj_id guards on dict?
|
|
0
|
189
|
December 5, 2024
|