Together AI research head explains kernels and self-optimizing inference
Together AI SVP of research Dan Fu explains kernels and a self-optimizing inference loop on The Compute 100 podcast, detailing how Together Compiler runs a model end-to-end, finds bottlenecks, and lets the model fix them itself.
2026-11-11 ~ 2026-11-12 · 2 related posts
- Together AI SVP Dan Fu on kernels, serving 3T-param models day zero, and self-improving inference — togethercompute · 2026-11-11
- Together Compiler explained: run the model, find bottlenecks, let the model fix them — togethercompute · 2026-11-12