zhuww

llama support inference？

2

May I ask when FastertTransformer can support llama's C++inference？

When using --use_precomputed_alignments, there is no need to use the pdb_mmcif dataset for template featurizer. Next time for inference, we can directly use the model file and the saved file,...

If I don't use the Docker container method and customize the compilation using tritonserver, using the corresponding server v2.33.0 according to 23.04, are there any requirements for this version?

Not found /software/rosetta/DAlphaBall.gcc

3

In line 32 of the scripts/get_interface_metrics.py , as follows： init('-corrections::beta_nov16 -holes:dalphaball /software/rosetta/DAlphaBall.gcc -detect_disulf false') What file is/software/rosetta/DAlphaBall.gcc here? I did not find it in the Rosetta source code.