Tutorials
Introducing ๐๐ฉ๐๐๐ฎ๐ฅ๐๐ญ๐ข๐ฏ๐ ๐๐๐๐จ๐๐ข๐ง๐ : ๐๐จ๐ฐ ๐๐ญ ๐๐ฏ๐จ๐ฅ๐ฏ๐๐, ๐๐ก๐๐ง ๐๐ญ ๐๐ญ๐๐ฒ๐ฌ ๐๐จ๐ฌ๐ฌ๐ฅ๐๐ฌ๐ฌ, ๐๐ง๐ ๐๐ก๐๐ญ'โฆ
Introducing ๐๐ฉ๐๐๐ฎ๐ฅ๐๐ญ๐ข๐ฏ๐ ๐๐๐๐จ๐๐ข๐ง๐ : ๐๐จ๐ฐ ๐๐ญ ๐๐ฏ๐จ๐ฅ๐ฏ๐๐, ๐๐ก๐๐ง ๐๐ญ ๐๐ญ๐๐ฒ๐ฌ ๐๐จ๐ฌ๐ฌ๐ฅ๐๐ฌ๐ฌ, ๐๐ง๐ ๐๐ก๐๐ญ'๐ฌ ๐๐๐ฑ๐ญ. An interactive tutorial @Madisonkanna and I built for the NeurIPS Education Track. Every LLM you use generate
Introducing ๐๐ฉ๐๐๐ฎ๐ฅ๐๐ญ๐ข๐ฏ๐ ๐๐๐๐จ๐๐ข๐ง๐ : ๐๐จ๐ฐ ๐๐ญ ๐๐ฏ๐จ๐ฅ๐ฏ๐๐, ๐๐ก๐๐ง ๐๐ญ ๐๐ญ๐๐ฒ๐ฌ ๐๐จ๐ฌ๐ฌ๐ฅ๐๐ฌ๐ฌ, ๐๐ง๐ ๐๐ก๐๐ญ'๐ฌ ๐๐๐ฑ๐ญ. An interactive tutorial @Madisonkanna and I built for the NeurIPS Education Track. Every LLM you use generates one token at a time. Autoregressive decoding is the bottleneck for inference. Speculative decoding accelerates this, and today it runs under nearly every hosted LLM. It is a cornerstone topic to learn in the LLM stack. Blog: https://neurips2026-speculative-decoding.vercel.app/
Related
- still many industry executives don't get the value of top-tier AI conf like ICML/ICLR/NeurIPS, they'd rather sit on some summit roundtable wโฆ
- Live now: our Memory & Continual Learning Track from AI Engineer World's Fair 2026. Thesis: we scaled intelligence and got the world's smartโฆ
- this seems quite doable in the space of a single 2-3 hour workshop โ any brave soul want to try to livecode this for people as a learning exโฆ
Source: Swyx (X) | 2026-09-06