-
Notifications
You must be signed in to change notification settings - Fork 2.4k
All issues
Issue creation is restricted in this repository
Issues
is:issue state:open
is:issue state:open
Search results
Myelin NVRTC compilation failure on Jetson Thor (SM110) building Fast-FoundationStereo - reproduces on TRT 10.14.1 and 11.2.1.2
Module:Embeddedissues when using TensorRT on embedded platformsissues when using TensorRT on embedded platformsModule:Engine BuildIssues with building TensorRT enginesIssues with building TensorRT enginesStatus: Open.#4830 In NVIDIA/TensorRT;TensorRT 11.0.0.114 builder finds no valid tactic for BF16 ConvTranspose2d (works fine in FP16)
Module:Engine BuildIssues with building TensorRT enginesIssues with building TensorRT enginesStatus: Open.#4829 In NVIDIA/TensorRT;Deprecate demoDiffusion
Module:DemoIssues regarding demos under the demo/ directory: Diffusion, DeBERTa, BertIssues regarding demos under the demo/ directory: Diffusion, DeBERTa, BertStatus: Open.#4827 In NVIDIA/TensorRT;TRT 11.2:
Transposeof a network input folded into a fused MHA operand with the permutation applied to the shape but not to the stridesModule:Engine BuildIssues with building TensorRT enginesIssues with building TensorRT enginesStatus: Open.#4826 In NVIDIA/TensorRT;Wrong encoder output for NeMo Parakeet (FastConformer) on RTX 5090 (sm_120a) — all precisions, all opt levels, TRT 10.14 and 11.1
Module:AccuracyOutput mismatch between TensorRT and other frameworksOutput mismatch between TensorRT and other frameworksStatus: Open.#4822 In NVIDIA/TensorRT;AveragePool fails at the exact batch boundary N=65536 on RTX 5090
Module:ONNXIssues relating to ONNX usage and importIssues relating to ONNX usage and importStatus: Open.#4821 In NVIDIA/TensorRT;YOLOv10 Error with TensorRT 10.13
Module:AccuracyOutput mismatch between TensorRT and other frameworksOutput mismatch between TensorRT and other frameworksStatus: Open.#4820 In NVIDIA/TensorRT;TRT 11.1 strongly-typed FP32 engine silently produces wrong results for a DETR-style detection model (correct in ONNXRuntime and TRT 10.13)
Module:AccuracyOutput mismatch between TensorRT and other frameworksOutput mismatch between TensorRT and other frameworksStatus: Open.#4813 In NVIDIA/TensorRT;ResizeWithPadPlugin — Aspect-Ratio-Preserving Resize with Padding
Feature RequestRequest for new functionalityRequest for new functionalityStatus: Open.#4811 In NVIDIA/TensorRT;instanceNormalizationPlugin: use public __half2float instead of private __internal_half2float
Module:PluginsIssues when using TensorRT pluginsIssues when using TensorRT pluginsStatus: Open.#4810 In NVIDIA/TensorRT;Concerns about TensorRT 11 mixed-precision workflow
Module:QuantizationIssues related to QuantizationIssues related to QuantizationStatus: Open.#4807 In NVIDIA/TensorRT;- Status: Open.#4806 In NVIDIA/TensorRT;