|
Disk Quota Exceeded error
|
|
4
|
551
|
May 30, 2024
|
|
Serving Torch_TersorRT converted model with Triton
|
|
0
|
152
|
April 25, 2024
|
|
Le: "b8[64, 2048, 7, 7]" = torch.ops.aten.le.Scalar(relu_48, 0); relu_48 = None
|
|
1
|
237
|
April 24, 2024
|
|
Torch.compile cache_size_limit best practice
|
|
1
|
560
|
April 12, 2024
|
|
Export and save problem（torch-tensorrt）
|
|
0
|
267
|
April 11, 2024
|
|
How to achieve Torch-MLIR compatibility with Dynamo backend?
|
|
1
|
323
|
April 9, 2024
|
|
[dynamo] [onnx] Models exported with torch.onnx.dynamo_export show worse performance during inference
|
|
0
|
302
|
April 8, 2024
|
|
Unique node name across graph re-compilations and graph breaks
|
|
0
|
211
|
April 3, 2024
|
|
Resetting cache in benchmark
|
|
3
|
1090
|
March 10, 2024
|
|
Timing model modules
|
|
0
|
189
|
March 6, 2024
|
|
Avoid loop unrolling with TorchDynamo for memory savings
|
|
0
|
266
|
March 4, 2024
|
|
Can save optimized_model created with torch_tensorrt.compile
|
|
3
|
1104
|
February 26, 2024
|
|
Torch.compile regularly fails with Triton Error [CUDA]: device kernel image is invalid
|
|
2
|
2895
|
February 23, 2024
|
|
Dynamo performance
|
|
0
|
250
|
February 23, 2024
|
|
Is Dynamo a good fit for high-level graph manipulation?
|
|
0
|
286
|
February 21, 2024
|
|
Unusual compiler behavior
|
|
0
|
237
|
February 20, 2024
|
|
How can I see the source of guards?
|
|
0
|
223
|
February 9, 2024
|
|
Compile source code, code navigation
|
|
2
|
356
|
February 9, 2024
|
|
Developer documentation for PyTorch 2.x compiler
|
|
12
|
952
|
February 6, 2024
|
|
BackendCompilerFailed: backend='inductor' raised: RuntimeError: Triton Error [CUDA]: device kernel image is invalid
|
|
2
|
2199
|
February 2, 2024
|
|
Does the order of graph_module.graph.nodes affect performance?
|
|
0
|
228
|
February 2, 2024
|
|
Where to PrimTorch's operator list?
|
|
2
|
497
|
January 18, 2024
|
|
UserDefinedObjectVariable should not be break renson
|
|
2
|
837
|
January 18, 2024
|
|
torch._dynamo.exc.Unsupported: Tensor.backward
|
|
6
|
2570
|
January 17, 2024
|
|
Easy way to check which guard fails in check_fn()
|
|
0
|
208
|
January 17, 2024
|
|
If I use torch.compile to compile the whole graph，in the my own compiler, how to manage the memory in my own compiler?
|
|
0
|
242
|
January 16, 2024
|
|
Type information for arguments of ATen operations
|
|
0
|
246
|
January 11, 2024
|
|
How to get whole graph when subgraph_compile triggle
|
|
2
|
836
|
January 8, 2024
|
|
What functions like torch._C._DisablePythonDispatcher do?
|
|
2
|
554
|
January 4, 2024
|
|
Torch.compile error for recurrent model
|
|
1
|
568
|
January 3, 2024
|