ChinaTalk· Aqib Zakaria·· 2 小时前AI 评分28
中国的 Groq 在哪里？
Where is China’s Groq?
AI 导读
ChinaTalk 发文追问“中国的 Groq 在哪里”，讨论 AI 推理芯片架构的分化。文章指出，2025 年底业界普遍认为 AI 推理必须依赖 HBM，因为推理解码是受内存带宽约束的操作，只有 HBM 能达到有效服务模型的带宽速度；但此后市场趋于成熟，已不再有单一架构通吃，不同芯片在训练、prefill 和 decode 上各有优势。
正文 · 原文
In late 2025, HBM was all the rage. You need HBM for AI inference; inference decode is a memory-constrained operation, and only HBM was able to reach bandwidth speeds to serve models effectively.
But the market has matured since then, and there is no longer one architecture to rule them all. Different silicon works better for training, prefill, or decode…
Subscribe for free to continue reading
Enter your email and get every post from ChinaTalk.
来源：ChinaTalk · chinatalk.media