Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Hackathon 2023 bug in tensorrt 9.0.0 #87

Open
yuanjiechen opened this issue Sep 7, 2023 · 0 comments
Open

Hackathon 2023 bug in tensorrt 9.0.0 #87

yuanjiechen opened this issue Sep 7, 2023 · 0 comments

Comments

@yuanjiechen
Copy link

yuanjiechen commented Sep 7, 2023

Reproduce code links: https://drive.google.com/file/d/1Kyw98JTrIokfcXkJBTv71lJOtwGcr2QF/view?usp=drive_link

Environment

If applicable, please include the following:
CPU architecture: x86_64
GPU properties
GPU name: NVIDIA A10
Clock frequencies used: None
Libraries
TensorRT branch: 9.0.0
TensorRT LLM: 0.1.3
Cuda: 12.1.66
Cudnn: unknown
Container: registry.cn-hangzhou.aliyuncs.com%2ftrt-hackathon%2ftrt-hackathon%3afinal_v1
NVIDIA driver version: 525.105.17
OS: Ubuntu 5.15.0-73

Reproduction Steps

Run sh preprocess.sh, build trt fp16 engine and compare with torch outputs

Expected Behaviour

Norm value < 100

Actural Behaviour

Norm value = 1316

Additional Notes

I have 20% time build good enging with norm < 100. I provide build logs in package: good.txt and bad.txt.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant