Description
When building a tensorRT engine with the flag trt.HardwareCompatibilityLevel.SAME_COMPUTE_CAPABILITY enabled, it fails with the error below:
Internal Error: MyelinCheckException: kernel_gen_ds.cpp:1147: CHECK(!redop->owner()->hardware_compute_capability_compatibility()) failed. In HCCC mode, we have disabled tiled reduce fusion under partition dag, so we should never enter here under HCCC mode.
[01/28/2026-08:55:25] [TRT] [E] Error Code: 9: Skipping tactic 0x0000000000000000 due to exception [myelin_graph.h:1182: attachExceptionMsgToGraph] MyelinCheckException: kernel_gen_ds.cpp:1147: CHECK(!redop->owner()->hardware_compute_capability_compatibility()) failed. In HCCC mode, we have disabled tiled reduce fusion under partition dag, so we should never enter here under HCCC mode. In compileGraph at /_src/optimizer/myelin/codeGenerator.cpp:1548
With the above flag disabled, everything works fine (but I wish this engine to be compatible on devices having the same compute compatibility).
Environment
TensorRT Version: 10.14.1
NVIDIA GPU: RTX4090
NVIDIA Driver Version: 535.230.02
CUDA Version: 12.2
CUDNN Version: 8.9
Operating System: Ubuntu 20.04 LTS
Python Version (if applicable): 3.10.12
Tensorflow Version (if applicable):
PyTorch Version (if applicable):
Baremetal or Container (if so, version):
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):