In the news
FuTransformer: FP8 prefill and INT4 decode for Llama-style inference on Hopper
arXiv cs.AI · Published · 3 min read
In 30 seconds
- cuda
- inference
- token
- llama
The Agent Architect
One pattern, one tradeoff, one production failure story. A short weekly briefing for people building agentic systems.
Weekly email, one-click unsubscribe. We only use your address to send the briefing.