llama support inference？

[double-vin]

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

[lvhan028]

Based on FasterTransformer, we have implemented an efficient inference engine - TurboMind, supporting both llama and llama-2

[byshiue]

FasterTransformer development has transitioned to TensorRT-LLM. TensorRT-LLM has supported LLaMa. Please take a try.