Assertion error in convertExplicitDDSPluginToImplicit.cpp: need help understanding the error.

Description

I am running into this error.
[06/17/2026-14:29:28] [TRT] [E] [convertExplicitDDSPluginToImplicit.cpp::convertExplicitDDSPluginToImplicit::149] Error Code 2: Internal Error (Assertion nodeIdxToDDSOutputIndices.count(i) == nodeIdxToSizeTensors.count(i) failed. In convertExplicitDDSPluginToImplicit at /_src/optimizer/myelin/rewrite/convertExplicitDDSPluginToImplicit.cpp:149)

I wish to understand the following,

• What does this file do? convertExplicitDDSPluginToImplicit.cpp
• What does this error mean? Error (Assertion nodeIdxToDDSOutputIndices.count(i) == nodeIdxToSizeTensors.count(i) failed. what is it checking?

Environment

TensorRT Version:
10.15.1

NVIDIA GPU:
5090

NVIDIA Driver Version:
580.159.03

CUDA Version:
12.8

CUDNN Version:
9.7.1

Operating System:
Ubuntu 22.04.4 LTS

Python Version (if applicable):
3.10.12

Tensorflow Version (if applicable):
N/A

PyTorch Version (if applicable):
2.7.0+cu128

Baremetal or Container (if so, version):
Docker container (Ubuntu 22.04 base)

TensorRT version:
10.15.1.29, GPU: RTX 5090.

Relevant Files

Model link:

Steps To Reproduce

Commands or scripts:

Have you tried the latest release?:

Attach the captured .json and .bin files from TensorRT's API Capture tool if you're on an x86_64 Unix system

Can this model run on other frameworks? For example run ONNX model with ONNXRuntime (polygraphy run <model.onnx> --onnxrt):

Start by reading convertExplicitDDSPluginToImplicit.cpp, especially the assertion reported at line 149. The issue provides no model, commands, reproduction steps, or capture files, so collect a minimal reproducer and the relevant TensorRT inputs before investigating. Done means explaining the assertion and identifying or narrowing the triggering model condition.