Skip to content

Actions: NVIDIA/TensorRT

Actions

Remove feedback label on comment

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
feedback-update.yml
383 workflow runs
383 workflow runs

Filter by Event

⌥ + click/return to exclude

Filter by Status

⌥ + click/return to exclude

Filter by Branch

⌥ + click/return to exclude

Filter by Actor

⌥ + click/return to exclude
Serialized engine size failure of TensorRT 11.2 when building an unfused pointwise op on a large activation on GPU H100 Remove feedback label on comment #579: Issue comment #4841 (comment) created by shssoichiro
1s
1s
The onnx parser failed to parse a valid model: Slice (importSlice): INVALID_NODE: Assertion failed: (starts.size() == axes.size()) Remove feedback label on comment #578: Issue comment #4470 (comment) created by njh1205
1s
1s
[Polygraphy] Add clear error for mismatched ONNX Slice input lengths (#4470) Remove feedback label on comment #577: Issue comment #4862 (comment) created by njh1205
12s
12s
[Polygraphy] Add clear error for mismatched ONNX Slice input lengths (#4470) Remove feedback label on comment #576: Issue comment #4862 (comment) created by pranavm-nvidia
1s
1s
The onnx parser failed to parse a valid model: Slice (importSlice): INVALID_NODE: Assertion failed: (starts.size() == axes.size()) Remove feedback label on comment #575: Issue comment #4470 (comment) created by pranavm-nvidia
1s
1s
The onnx parser failed to parse a valid model: Slice (importSlice): INVALID_NODE: Assertion failed: (starts.size() == axes.size()) Remove feedback label on comment #574: Issue comment #4470 (comment) created by njh1205
1s
1s
Remove feedback label on comment Remove feedback label on comment #573: created by njh1205
10s
10s
TRT 11.3: Attention does not compile inside If, even with decomposable=True Remove feedback label on comment #572: Issue comment #4860 (comment) created by ws30
1s
1s
polygraphy run failed on Polygraphy Version: 0.49.20. when will update FormattedArray to support reformated model input/output tensor, such as fp16:hwc8 Remove feedback label on comment #571: Issue comment #4685 (comment) created by somtri
8s
8s
onnx_graphsurgeon.GraphPattern()：The order in which the nodes are added affects the success of the match. Remove feedback label on comment #570: Issue comment #4377 (comment) created by somtri
1s
1s
LSTM model converted to TensorRT is slower than PyTorch on RTX 4090 Remove feedback label on comment #569: Issue comment #4490 (comment) created by nMoussa
8s
8s
Polygraphy only supports a single input sample (iteration) during debug reduce Remove feedback label on comment #568: Issue comment #4607 (comment) created by timothyanderson096-ocdealcheck
1s
1s
Myelin "Could not infer output types for operation: dequantize" on SM 8.7 (Orin); identical engine builds on SM 11.0 (Thor) with the same TensorRT 10.16.2.10 Remove feedback label on comment #567: Issue comment #4832 (comment) created by kvnloo
Skipped
Skipped
TRT 11.1 strongly-typed FP32 engine silently produces wrong results for a DETR-style detection model (correct in ONNXRuntime and TRT 10.13) Remove feedback label on comment #566: Issue comment #4813 (comment) created by kvnloo
1s
1s
TRT 11.2: Transpose of a network input folded into a fused MHA operand with the permutation applied to the shape but not to the strides Remove feedback label on comment #565: Issue comment #4826 (comment) created by kvnloo
1s
1s
TensorRT Build Error: Tensor Volume Exceeds 2^31 Limit for Large Fixed Shapes (Super-Resolution/Restoration Models) Remove feedback label on comment #564: Issue comment #4408 (comment) created by kvnloo
1s
1s
DINOv2 (Vision Transformer) FMHA Fusion Failure in TensorRT 10.8.0.43 with PyTorch 2.7.1 ONNX Export (with GPU 3080) Remove feedback label on comment #563: Issue comment #4537 (comment) created by kvnloo
1s
1s
Precision/behavior failure of TensorRT 10.12 when running mixed FP32/FP16 image restoration on GPU RTX 3080 Laptop Remove feedback label on comment #562: Issue comment #4645 (comment) created by kvnloo
1s
1s
LSTM model converted to TensorRT is slower than PyTorch on RTX 4090 Remove feedback label on comment #561: Issue comment #4490 (comment) created by kvnloo
1s
1s
[Feature Request] TRT_MoE Support for older GPU architectures (sm90, sm89, sm80) Remove feedback label on comment #560: Issue comment #4805 (comment) created by kvnloo
2s
2s
TensorRT silently produces wrong results for batch > 1 on SegFormer (b0/b1/b2 verified, fp32, static and dynamic engines, TRT 10.11 & 11.1, sm89 + sm120) Remove feedback label on comment #559: Issue comment #4853 (comment) created by kvnloo
1s
1s
Wrong FP16 results when a fused convolution, activation and residual add reads a strided concat view Remove feedback label on comment #558: Issue comment #4854 (comment) created by kvnloo
1s
1s
W4A16 FP4 build succeeds while silently realizing FP32 (no warning, no refusal) Remove feedback label on comment #557: Issue comment #4833 (comment) created by kvnloo
1s
1s
AOT plugins leak CUDA modules on dynamic-shape changes in TensorRT 11.1/11.2.1 Remove feedback label on comment #556: Issue comment #4849 (comment) created by kvnloo
1s
1s
polygraphy run failed on Polygraphy Version: 0.49.20. when will update FormattedArray to support reformated model input/output tensor, such as fp16:hwc8 Remove feedback label on comment #555: Issue comment #4685 (comment) created by kvnloo
8s
8s