Fast Inference on Large Language Models: BLOOMZ on Habana Gaudi2 Accelerator

T1Covered by 1 source · first reported by Hugging Face Blog at 28 Mar 2023, 00:00 UTC

ai

Sources

• T1Fast Inference on Large Language Models: BLOOMZ on Habana Gaudi2 AcceleratorHugging Face Blog28 Mar 2023, 00:00