|
About the torch._dynamo category
|
|
0
|
575
|
December 6, 2022
|
|
AssertionError: Dict types must use ConstDictVariable
|
|
1
|
29
|
September 9, 2024
|
|
Understanding dynamic shapes and guards and when it does/does not cause graph breaks
|
|
1
|
23
|
August 28, 2024
|
|
How to gracefully mask CompositeImplicitAutograd for different backends
|
|
0
|
20
|
August 26, 2024
|
|
Torch_tensorrt compile for a range of sizes with steps
|
|
1
|
21
|
August 17, 2024
|
|
Is there any way to get traced GraphModule without creating torch dynamo's constraint guards?
|
|
0
|
12
|
August 1, 2024
|
|
Unsupported FX node: <built-in function mod>
|
|
0
|
15
|
July 29, 2024
|
|
Any chance to torch.export TorchScript?
|
|
1
|
155
|
July 29, 2024
|
|
NvFuser with torch.compile
|
|
8
|
1190
|
July 11, 2024
|
|
Windows support timeline for torch.compile
|
|
6
|
4886
|
July 8, 2024
|
|
torch._dynamo.exc.Unsupported: call_method NNModuleVariable() _sa_block [TensorVariable(), LazyVariableTracker(), LazyVariableTracker()] {}
|
|
0
|
257
|
June 1, 2024
|
|
How to customize leaf node in dynamo trace?
|
|
1
|
387
|
May 31, 2024
|
|
Issue with max-autotune mode in torch.compile
|
|
1
|
243
|
May 30, 2024
|
|
Disk Quota Exceeded error
|
|
4
|
259
|
May 30, 2024
|
|
Fatal error: pyconfig.h: No such file or directory
|
|
2
|
398
|
May 24, 2024
|
|
Serving Torch_TersorRT converted model with Triton
|
|
0
|
138
|
April 25, 2024
|
|
Slow convolutions in triton
|
|
0
|
200
|
April 24, 2024
|
|
Le: "b8[64, 2048, 7, 7]" = torch.ops.aten.le.Scalar(relu_48, 0); relu_48 = None
|
|
1
|
191
|
April 24, 2024
|
|
Torch.compile cache_size_limit best practice
|
|
1
|
307
|
April 12, 2024
|
|
Export and save problem（torch-tensorrt）
|
|
0
|
226
|
April 11, 2024
|
|
How to achieve Torch-MLIR compatibility with Dynamo backend?
|
|
1
|
237
|
April 9, 2024
|
|
The difference between `torch.ops.aten.addmm.default` and `torch.ops.aten.linear.default`
|
|
0
|
295
|
April 8, 2024
|
|
[dynamo] [onnx] Models exported with torch.onnx.dynamo_export show worse performance during inference
|
|
0
|
250
|
April 8, 2024
|
|
Unique node name across graph re-compilations and graph breaks
|
|
0
|
185
|
April 3, 2024
|
|
Resetting cache in benchmark
|
|
3
|
717
|
March 10, 2024
|
|
Timing model modules
|
|
0
|
165
|
March 6, 2024
|
|
Avoid loop unrolling with TorchDynamo for memory savings
|
|
0
|
220
|
March 4, 2024
|
|
Can save optimized_model created with torch_tensorrt.compile
|
|
3
|
772
|
February 26, 2024
|
|
Torch.compile regularly fails with Triton Error [CUDA]: device kernel image is invalid
|
|
2
|
2487
|
February 23, 2024
|
|
Dynamo performance
|
|
0
|
209
|
February 23, 2024
|