NVIDIA / NVIDIA/TensorRT

trt failure of TensorRT 10.13.2 RTX5070-CUDA12.4-cudnn8.9.7

Open
#4,569 2 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Module:Engine Build
Dominant language
C++
Stars
13.4k
Forks
2.4k
Avg merge
5d 3h
Merged PRs (30d)
2

Description

[09/08/2025-16:33:58] [I]
[09/08/2025-16:33:58] [I] TensorRT version: 10.13.2
[09/08/2025-16:33:58] [I] Loading standard plugins
[09/08/2025-16:33:58] [I] [TRT] [MemUsageChange] Init CUDA: CPU +1, GPU +0, now: CPU 13086, GPU 1238 (MiB)
[09/08/2025-16:33:59] [E] [TRT] [builder.cpp::nvinfer1::builder::createCaskKernelLibraryImpl::157] Error Code 2: Internal Error (Assertion validateCaskKLibSize(buffer.size) failed. )
[09/08/2025-16:33:59] [E] Builder creation failed
[09/08/2025-16:33:59] [E] Failed to create engine from model or file.
[09/08/2025-16:33:59] [E] Engine set up failed
&&&& FAILED TensorRT.trtexec [TensorRT v101302] [b6] # trtexec.exe --onnx=yolov8n.onnx --saveEngine=best.trt

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

No source file or test is mentioned. Start by reproducing the failure with trtexec.exe, TensorRT 10.13.2, yolov8n.onnx, and the reported RTX5070/CUDA environment; compare the log through builder creation. Done means identifying the cause of the assertion and confirming that the model engine can be created successfully.

Written by the indexing model from the issue text.

Assessment

Tech stack
cpp
Domain
machine-learning
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.