1 Release published by 1 person

• v10.12.0 TensorRT 10.12 Release

  published Jun 18, 2025

1 Pull request merged by 1 person

• TensorRT 10.12 OSS Release

  #4491 merged Jun 18, 2025

3 Issues closed by 3 people

• ONNX model conversion failure of TensorRT 10.3 when running trtexec on GPU Jetson Orin

  #4494 closed Jun 21, 2025

• HuggingFace DETR model export fails

  #4477 closed Jun 19, 2025

• How to use custom ops (load xx.so for ort) with polygraph run --onnxrt ?

  #4487 closed Jun 19, 2025

4 Issues opened by 4 people

• When will the deformable_aggregation operator be supported? I used a custom plugin but it took too much time.

  #4496 opened Jun 23, 2025

• Build failure for onnx-graphsurgeon with onnx 1.18.0

  #4495 opened Jun 22, 2025

• layernorm fp16, The accuracy is still insufficient

  #4493 opened Jun 18, 2025

• Accuracy problem between onnx and fp16 trt inference

  #4492 opened Jun 18, 2025

15 Unresolved conversations

Sometimes conversations happen on old items that aren’t yet closed. Here is a list of all the Issues and Pull Requests with unresolved conversations.

• Failure of TensorRT 10.7 when running inference on A4500

  #4411 commented on Jun 17, 2025 • 0 new comments

• failure of SigLIP2 FP32 to FP16

  #4373 commented on Jun 18, 2025 • 0 new comments

• detectron2 faster rcnn to tensor rt

  #4466 commented on Jun 18, 2025 • 0 new comments

• Builder failure of TensorRT 8.5 when trying to run on DLA of Jetson Orin

  #4413 commented on Jun 18, 2025 • 0 new comments

• demo_img2vid: Error Code 1: Cuda Runtime (out of memory)

  #4353 commented on Jun 18, 2025 • 0 new comments

• after converting onnx fp32 to int8 engine with custom calibration, the engine layers still show fp32

  #4341 commented on Jun 18, 2025 • 0 new comments

• TensorRT‌ 10.3 wrong results!

  #4330 commented on Jun 18, 2025 • 0 new comments

• Significant output discrepancy between TensorRT engine and ONNX Runtime inference outputs

  #4415 commented on Jun 19, 2025 • 0 new comments

• Abnormal of onnx model to trt model in the inference results

  #4125 commented on Jun 19, 2025 • 0 new comments

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

  #4490 commented on Jun 19, 2025 • 0 new comments

• Invalid node error when generating model engine using trtexec for onnx model "ESS DNN stereo disparity" from NGC catalog

  #4488 commented on Jun 19, 2025 • 0 new comments

• Export failure of TensorRT 10.11 when running scaled dot product on GPU A6000

  #4482 commented on Jun 19, 2025 • 0 new comments

• "Internal Error: MyelinCheckException: gvn.cpp:318: CHECK(graph().ssa_validation()) failed." when building engine

  #4468 commented on Jun 20, 2025 • 0 new comments

• failed to build the serialized network due to the wrong shape inference of the LayerNormalization operator

  #4475 commented on Jun 20, 2025 • 0 new comments

• Error Code 1: Myelin ([cask.cpp:exec:972] Platform (Cuda) error

  #4080 commented on Jun 23, 2025 • 0 new comments