Published onSeptember 13, 2022Accelerate GPT-J inference with DeepSpeed-Inference on GPUs#GPTJ#DeepSpeed#HuggingFace#OptimizationLearn how to optimize GPT-J for GPU inference with a 1-line of code using Hugging Face Transformers and DeepSpeed.Read more →
Published onAugust 16, 2022Accelerate BERT inference with DeepSpeed-Inference on GPUs#BERT#DeepSpeed#HuggingFace#OptimizationLearn how to optimize BERT for GPU inference with a 1-line of code using Hugging Face Transformers and DeepSpeed.Read more →