What’s Cooking

NVIDIABlog26 Jun

Creating the NVIDIA Nemotron 3 Ultra NVFP4 Checkpoint with NVIDIA Model Optimizer

Hugging FaceBlog26 Jun

Run a vLLM Server on HF Jobs in One Command

DropboxBlog25 Jun

How we used DSPy to turn AI evaluations into better responses in Dash chat

LambdaBlog25 Jun

What happens when Claude Code gets an experiment tracker

H2O.aiBlog24 Jun

Open-weight H2O Danube3 Series

H2O.aiBlog24 Jun

H2O LLM Studio

ModalBlog24 Jun

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

CerebrasBlog24 Jun

Never Loop Without Verifiers

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

RedisBlog23 Jun

Context engineering vs prompt engineering: the difference

ModalBlog23 Jun

Introducing Modal Auto Endpoints: Optimized inference you actually own

Hugging FaceBlog22 Jun

DeepSeek-V4: a million-token context that agents can actually use

You’re caught up

That’s every post that week in this feed.

15–21 Jun 2026