Glossary · Term

VeOmni

← all terms

Definition

Plain language

A real AI training system whose hand-tuned GPU code was used as the benchmark an AI had to beat.

As stated in the literature

A production mixture-of-experts training framework whose expert-written Triton weight-gradient kernel served as the human baseline that KernelPro's from-scratch CUDA kernel surpassed.

Why it matters: Using real expert-tuned production code as the bar makes any claim of beating it meaningful, rather than winning against a weak straw-man baseline.

For example, VeOmni's carefully hand-written GPU code for a key training step was the human-made benchmark that an AI-generated kernel had to outperform.

Heard on the show

“There's a kernel inside a real training system called VeOmni — a weight-gradient kernel for a mixture-of-experts model — that had been hand-tuned in Triton by expert engineers.”
Episode 177 — Why Raw Profiler Data Made an AI Worse at Writing GPU Code

Mentioned in 1 episode

  1. 177
    Why Raw Profiler Data Made an AI Worse at Writing GPU Code

Related terms