英伟达称Groq 3 LPX推理芯片比Cerebras快四倍，但实际更复杂

Nvidia is moving its Groq 3 LPX inference chip into full production and reports 3,400 tokens per second on Gemma 4 31B, four times faster than Cerebras. But the numbers don't tell the whole story. Nvidia needs at least 64 accelerators to get there, while Cerebras needs only one or two, according to The Register. How well the architecture scales with large MoE models remains an open question.