ChinaTalk· Aqib Zakaria·· 22 days ago35
Where is China’s Groq?
Where is China’s Groq?
Brief overview
HBM was once popular at the end of 2025, as it could meet AI inference needs through high bandwidth, but the market has matured, single architecture no longer dominates, and different chips perform differently in training, pre-fetching, or decoding.
Article
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.
Source: ChinaTalk · chinatalk.media