What’s Cooking

BasetenBlog25 Jun

Live draft model training for speculative decoding

ModalBlog24 Jun

Achieve state-of-the-art inference latencies with speculative decoding

NVIDIABlog23 Jun

Boost Inference Performance up to 15x on NVIDIA Blackwell Using DFlash Speculative Decoding

BasetenBlog23 Jun

How we built the world’s fastest API for GLM-5.2

ModalBlog23 Jun

Introducing Modal Auto Endpoints: Optimized inference you actually own

You’re caught up

That’s every post that week in this feed.

15–21 Jun 2026