Open yuanjiechen opened 1 year ago
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.
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
Expected Behaviour
Actural Behaviour
Additional Notes