Groq LPU
Language Processing Unit purpose-built for low-latency LLM inference
N/A
Accelerator
0.23GB
SRAM
80000
GB/s bandwidth
// about Groq LPU
Language Processing Unit purpose-built for low-latency LLM inference
// similar hardware in Accelerator
Google TPU v5p
Google custom AI accelerator for training large models on Cloud TPU pods
Google · Accelerator · N/A
Google TPU v5e
Cost-efficient TPU generation for training and inference
Google · Accelerator · N/A
Intel Gaudi 3
Intel third-generation AI training and inference accelerator
Intel · Accelerator · N/A