Too little, too late? Bertha Language Processing Unit joins Groq’s ultrafast LPU as challenge to Nvidia’s formidable GPU firepower grows
South Korean AI startup HyperAccel partnered with platform-based SoC and ASIC designer SEMIFIVE back in January 2024, to develop the Bertha LPU. Tailored for LLM… Read More »Too little, too late? Bertha Language Processing Unit joins Groq’s ultrafast LPU as challenge to Nvidia’s formidable GPU firepower grows