Together Compiler explained: run the model, find bottlenecks, let the model fix them
togethercompute · x · 2026-11-12
Together AI's Together Compiler, explained by Dan Fu on The Compute 100 podcast, works in three steps: (1) run the model end to end, (2) find the bottlenecks, (3) let the model fix them—using AI to automate kernel and infrastructure optimization instead of manual tuning.
Related event: Together AI research head explains kernels and self-optimizing inference(2 posts)→
More from Infra
- LeapQuant: training-free quantization makes linear attention up to 4.25x faster — tianyin_xu · 2026-11-12
- Microsoft's MAI Transcribe 2 sees 12x usage growth, hitting 8.5M weekly transcriptions — mustafasuleyman · 2026-11-12
- gVisor joins CNCF with Modal as co-maintainer after upstreaming GPU and training support — josh_wills · 2026-11-12
- Local vs Cloud AI Coding Agents: Benchmarks, Hardware Costs, Performance — luisdans · 2026-11-12
- Agent Substrate 1.0 GA: microVM-sandboxed agent runtime with zero ambient credentials — rakyll · 2026-11-12
- WSJ: Nvidia is preparing to oust CEO Jensen Huang — jbredeche · 2026-11-12