Closed leeeizhang closed 1 week ago
The torchscript frontend does not support BF16 however the Dynamo frontend does. If you would like to use torchscript for deployment you can still torch.jit.trace
the result of compile with the Dynamo frontend and use it as you would with the original torchscript method
The torchscript frontend does not support BF16 however the Dynamo frontend does. If you would like to use torchscript for deployment you can still
torch.jit.trace
the result of compile with the Dynamo frontend and use it as you would with the original torchscript method
many thanks! it works for me.
What you have already tried
The nvidia tensorrt has already support the
bf16
precision after tensorrt>=9.2:However, the latest torch_tensorrt (
torch_tensorrt==2.3.0 w/ tensorrt==10.0.1
) has not support this.Is there any plan to support bfloat16 in future verisons? The bf16 is very popular in the LLM inference.
Environment
conda
,pip
,libtorch
, source): pip3 install torch_tensorrt==2.3.0 tensorrt==10.0.1