loading
loading
Where is China’s Groq? Why isn’t China making HBM-free chips? 36 4 Share 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.
document fetched 2026-10-24 02:55 · canonical https://chinatalk.media/p/where-is-chinas-groq