Together AI SVP Dan Fu on kernels, serving 3T-param models day zero, and self-improving inference
togethercompute · x · 2026-11-11
Together AI SVP of Research Dan Fu appeared on The Compute 100 podcast covering what a kernel actually is, how a 3T-parameter model gets served on day zero, and how Together Compiler uses AI to improve inference. He notes models are now good enough to apply to their own inference workloads — an RSI loop for inference is starting to deliver on its promise.
More from Infra
- Apple reportedly building Harbor app to turn Macs into private AI inference servers with Thunderbolt 5 clustering — BenBajarin · 2026-11-11
- Agent Arena: Gemini 4 Carbon Gets More Cost-Competitive as Tasks Get Harder — rseroter · 2026-11-11
- AMD Zen 6 deep dive: cheaper branch mispredicts and a return to Zen 3/4 integer scheduling — jedisct1 · 2026-11-11
- ExecuTorch adds WebGPU backend: run PyTorch models in-browser, up to 10x faster than CPU — PyTorch · 2026-11-11
- Hedra runs training experiments with AI agents steered by human researchers — testingcatalog · 2026-11-11
- Simular Box gives Claude, ChatGPT and Cursor agents their own cloud Linux desktop via MCP — AdFluid9823 · 2026-11-11