Agentic AI news, research notes, and industry analysis.

Tag

Optimization

2 stories in this tag.

· AI Beat Desk

A Trillion Parameters at a Thousand Tokens Per Second

Xiaomi and TileRT published MiMo-V2.5-Pro-UltraSpeed on June 8, pushing a one-trillion-parameter model past 1000 tokens per second on a single standard 8-GPU node — no custom silicon, just three carefully chosen co-design decisions applied to a commodity cluster.

Read more →
· AI Beat Desk

Read First, Then Code

SkyPilot published an experiment where giving Claude Code research papers to read before it optimized llama.cpp's CPU backend yielded 15% faster text generation on x86 for about $29. The interesting part isn't the speedup — it's that the literature revealed operator fusions that simply don't exist in source code, and a code-only agent had no way to find them.

Read more →