nvluxiaoz

Results 4 comments of nvluxiaoz

The issue with Llama when trying to create the: checkpoint: does not appear config.json

If it is a Meta checkpoint, you may need to try `--meta_ckpt_dir` instead of `--model_dir`?

Why can't we set the precision of all layers to fp16 or fp32?

I think you might do ``` if layer.precision == trt.float16: layer.precision == trt.float32 ```

set fp32 for MatMul failure of TensorRT 8.6.1.1 when converting onnx to trt with version 8.6.1.1

Have you tried to use the ToT version? (e.g. 10.2) I think because you are using weakly_typed networks and I assume you enabled fp16 flags, you will need to set...

bug: huggingface-hub 1.0.0 release breaks existing evaluate releases

by the way `evaluate==0.4.5` is forced by my own software. It worked all fine previously but broke yesterday.