INT21: 2 engineers direct AI to build 20 inference engines in 2 weeks, up to 2.4× faster than SGLang
bingxu_ · x · 2026-10-03
Startup INT21 says two engineers directed AI to build 20 full inference engines in two weeks: text generation beat SGLang on all six models tested (up to 2.4× faster), audio generation up to 7.5× faster than vLLM. Its CEO told Business Insider that scarce CUDA talent is now being augmented by AI, as engineers shift from hand-writing kernels to directing AI. Bing Xu adds: agent evolution marks the beginning of the end of hand-written GPU kernels.
More from coding & agent
- System prompts as products: a dev's take on the proactive agent era — _AustinCalvert_ · 2026-10-03
- Dev finds 50,000 words of hidden Claude memory notes polluting his context even with memory off — repligate · 2026-10-03
- Stardock launches Clairvoyance AI tool, says it may become its top revenue source — draginol · 2026-10-03
- GitHub's gh-stack v0.2.0 adds git worktree support for stacked PR workflows — mariorod1 · 2026-10-03
- Enterprise AI Adoption Beyond Coding Is Still at the Starting Line — brandon_galang · 2026-10-03
- ChatGPT Sites hits Hacker News: prototype in an hour, mostly positive takes — simpsoka · 2026-10-03