SambaNova Adds HBM for LLM Inference Chip

The startup claims it can serve 5-trillion-parameter models with 256k+ sequence length.

The post SambaNova Adds HBM for LLM Inference Chip appeared first on EE Times.

ai ai accelerator ai and big data ai and machine learning ai and ml ai-based chips ai chip ai chips chip hbm hbm3 inference llm llms ml ml inference sambanova serve startup