Smarter-version comments

Repositories
Issues
Comments

Results 4 comments of


                                            Smarter-version

When the code is release?

Set layernorm to fp32 failure of TensorRT v8.6.11 when running trtexec on GPU A100

I'm having the same problem. Have you solved it?

Set layernorm to fp32 failure of TensorRT v8.6.11 when running trtexec on GPU A100

I want to modify the precision of the Add_3244 node to fp32, but it's wrapped in Myelin. Commands or scripts: trtexec \ --onnx=$onnx_path \ --saveEngine=$engine_path \ --plugins=$plugins_path \ --verbose --workspace=2048...

Set layernorm to fp32 failure of TensorRT v8.6.11 when running trtexec on GPU A100

> > I want to modify the precision of the Add_3244 node to fp32, but it's wrapped in Myelin. Commands or scripts: trtexec --onnx=$onnx_path --saveEngine=$engine_path --plugins=$plugins_path --verbose --workspace=2048 --exportProfile=${engine_path}.profile.json --exportLayerInfo=${engine_path}.graph.json...