Zero Zeng

A similar issue: https://github.com/NVIDIA/TensorRT/issues/3257

> @zerollzeng is this dup of #3257 ? thanks Maybe not. > absolute difference: min: 9.02219e-10 (0.000139833, 0.000139832), max: 0.00138001 (0.0436334, 0.0450134), mean: 9.89399e-06 > relative difference: min: 5.52027e-06 (0.0022354,...

output data range. e.g if the range is [-1, 1], then the diff(max 0.001) look good to me.

> But the relative difference is too big if trt output has value 0.000001 and the onnx output has value 0.000002. then you will see the a relative difference of...

Okay, I think we need a reproduce to debug this issue further.

> I see the description `"Format/Datatype": "Channel major FP16 format where channel % 8 == 0"` and `"Format/Datatype": "Channel major FP16 format where channel % 2 == 0"`. I don't...

> [05/15/2024-20:44:50] [E] Saving engine to file failed. no disk space?

Please check our release note, I think you need at least TRT 8.6 or 9.0, can't remember exactly which one.

If you can export then in a single onnx model, I think then you are done. Please correct me if I understand wrong.

Or you can build multiple engines and put them inside a cuda stream.