Repository Issue Activity (beta)

#4551 Incorrect CumSum outputs since TensorRT 10.8+

#4846 Incorrect output failure of TensorRT 11.1 and 11.2 when running dynamic If → Transpose → Resize on GPU GTX 1660 SUPER and A10G

#4841 Serialized engine size failure of TensorRT 11.2 when building an unfused pointwise op on a large activation on GPU H100

#4845 TensorRT 10.14+ multi-GPU build regression with Cask-backed ops

#4571 ERROR when reducing (onnx) model inputs using Polygraphy

#2082 fp16 output mismatch

#4833 W4A16 FP4 build succeeds while silently realizing FP32 (no warning, no refusal)

#4832 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

#4842 BF16 strongly-typed engine build SIGSEGVs in Myelin on RTX 5090 (sm_120) for DETR-family transformer — identical graph builds fine as FP16 (reproduced on 11.0.0.114 / 11.1.0.106 / 11.2.1.2)

#4838 FP16 model compilation failure with TensorRT 11.2.1.2 on 4090 RTX

#4840 Segmentation fault in TensorRT 10.3 during Myelin compilation of PointCNN-style model on Jetson Orin NX

#4837 Silently incorrect fp16/bf16 outputs from fused MHA on consumer Blackwell (sm_120) for ViT/DETR model (SAM 3 detector) — fp32 exact, persists in 10.16.1, breaking the MHA fusion restores accuracy

#4831 [Architecture Discussion] Overhead and safety of asynchronous soft-stop signaling for KV-cache reclamation during generation loops

#4829 TensorRT 11.0.0.114 builder finds no valid tactic for BF16 ConvTranspose2d (works fine in FP16)

#4830 Myelin NVRTC compilation failure on Jetson Thor (SM110) building Fast-FoundationStereo - reproduces on TRT 10.14.1 and 11.2.1.2

#4813 TRT 11.1 strongly-typed FP32 engine silently produces wrong results for a DETR-style detection model (correct in ONNXRuntime and TRT 10.13)

#4827 Deprecate demoDiffusion

#4826 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

#4490 LSTM model converted to TensorRT is slower than PyTorch on RTX 4090

#4804 How to close part of fusions in TensorRT 10.16

#4408 TensorRT Build Error: Tensor Volume Exceeds 2^31 Limit for Large Fixed Shapes (Super-Resolution/Restoration Models)

#4822 Wrong encoder output for NeMo Parakeet (FastConformer) on RTX 5090 (sm_120a) — all precisions, all opt levels, TRT 10.14 and 11.1

#4821 AveragePool fails at the exact batch boundary N=65536 on RTX 5090

#4817 Integer by zero crash when trying FP8 quantization inference

#4820 YOLOv10 Error with TensorRT 10.13