|
Is there any way to save multiple graphs from same model without redundantly saving their state dicts?
|
|
0
|
28
|
October 2, 2024
|
|
Fatal error: pyconfig.h: No such file or directory
|
|
3
|
1475
|
September 17, 2024
|
|
Unsupported FX node: <built-in function mod>
|
|
1
|
203
|
September 12, 2024
|
|
AssertionError: Dict types must use ConstDictVariable
|
|
1
|
207
|
September 9, 2024
|
|
Understanding dynamic shapes and guards and when it does/does not cause graph breaks
|
|
1
|
192
|
August 28, 2024
|
|
How to gracefully mask CompositeImplicitAutograd for different backends
|
|
0
|
110
|
August 26, 2024
|
|
Torch_tensorrt compile for a range of sizes with steps
|
|
1
|
38
|
August 17, 2024
|
|
Is there any way to get traced GraphModule without creating torch dynamo's constraint guards?
|
|
0
|
34
|
August 1, 2024
|
|
Any chance to torch.export TorchScript?
|
|
1
|
308
|
July 29, 2024
|
|
NvFuser with torch.compile
|
|
8
|
1717
|
July 11, 2024
|
|
Windows support timeline for torch.compile
|
|
6
|
7054
|
July 8, 2024
|
|
Issue with max-autotune mode in torch.compile
|
|
1
|
1382
|
May 30, 2024
|
|
Disk Quota Exceeded error
|
|
4
|
1007
|
May 30, 2024
|
|
Serving Torch_TersorRT converted model with Triton
|
|
0
|
166
|
April 25, 2024
|
|
Le: "b8[64, 2048, 7, 7]" = torch.ops.aten.le.Scalar(relu_48, 0); relu_48 = None
|
|
1
|
303
|
April 24, 2024
|
|
Torch.compile cache_size_limit best practice
|
|
1
|
1092
|
April 12, 2024
|
|
Export and save problem（torch-tensorrt）
|
|
0
|
309
|
April 11, 2024
|
|
How to achieve Torch-MLIR compatibility with Dynamo backend?
|
|
1
|
443
|
April 9, 2024
|
|
[dynamo] [onnx] Models exported with torch.onnx.dynamo_export show worse performance during inference
|
|
0
|
354
|
April 8, 2024
|
|
Unique node name across graph re-compilations and graph breaks
|
|
0
|
252
|
April 3, 2024
|
|
Timing model modules
|
|
0
|
219
|
March 6, 2024
|
|
Avoid loop unrolling with TorchDynamo for memory savings
|
|
0
|
320
|
March 4, 2024
|
|
Can save optimized_model created with torch_tensorrt.compile
|
|
3
|
1469
|
February 26, 2024
|
|
Torch.compile regularly fails with Triton Error [CUDA]: device kernel image is invalid
|
|
2
|
3593
|
February 23, 2024
|
|
Dynamo performance
|
|
0
|
285
|
February 23, 2024
|
|
Is Dynamo a good fit for high-level graph manipulation?
|
|
0
|
296
|
February 21, 2024
|
|
Unusual compiler behavior
|
|
0
|
277
|
February 20, 2024
|
|
How can I see the source of guards?
|
|
0
|
225
|
February 9, 2024
|
|
Compile source code, code navigation
|
|
2
|
452
|
February 9, 2024
|
|
Developer documentation for PyTorch 2.x compiler
|
|
12
|
1041
|
February 6, 2024
|