Tagged: aws-inferentia2

4 articles

Latest

AWS Inferentia2 cuts Hugging Face model latency 4.5x over NVIDIA A10G GPUs

Llama 2 now runs on AWS Inferentia2, and the numbers are surprising

Hugging Face opens 100,000 models to AWS Inferentia2 deployment

Hugging Face TGI hits AWS Inferentia2, cutting GPU dependence for LLM deployments