Dedicated Processor IP
and Server Appliance
for Generation Workloads
LPU-based datacenter server outperforms state-of-the art DGX A100 in text generation workloads, such as ChatGPT, in terms of performance (>30%), cost-effectiveness (>2x), and power efficiency (>2x), with a superior accelerator scalability LEARN MORE
To be updated
Coming Soon.
Silicon IP
Latency Processing Unit (LPU) IP
Highly optimized and flexible processor IP that is able to reconfigure both memory types and compute resources for low-power or high-performance during LLM inference depending on customer needs