AI EngineerTwo Minute PapersNVIDIABasetenDecagonModalAppleCohere+6

AI EngineerYouTube14h

How Inference Keeps Up with Our Insatiable Need for Tokens — Cerebras & Gimlet Labs

AI EngineerYouTube1d

Same Model, Different Speed: Why Your Inference Provider Matters — FriendliAI

AI EngineerYouTube5d

Is Speculative Decoding Worth It? Profiling vLLM on NVIDIA Blackwell — Akamai

AI EngineerYouTube6d

What Is an Inference Engine, Anyway? — Charles Frye, Modal

Two Minute PapersYouTube1w

The Billion Dollar AI Advantage Is Disappearing

AI EngineerYouTube1w

What Makes Open Models Fast in Production — Sujee Maniyam, Nebius

NVIDIABlog4 Sept

Frontier Reasoning Reaches the Edge: How to Deploy and Optimize Models on NVIDIA Jetson

NVIDIABlog2 Sept

Co-Designing AI Models Using Speculative Decoding for Faster LLM Inference

BasetenBlog2 Sept

The efficient frontier of LLM inference

BasetenBlog28 Aug

GLM 5.3: Scaling with post-training, intuitively explained

BasetenBlog14 Aug

Inference engineering for DeepSeek V4 Pro 0813

DecagonBlog13 Aug

How Decagon shipped real-time voice AI on Modal

ModalBlog12 Aug

Qwen3.8-2.4T-A95B now available on Modal

AppleBlog7 Aug

Arbitrage: Efficient Reasoning via Advantage-Aware Speculation

CohereBlog30 Jul

Why MoE Models Get More From Speculative Decoding

ModalBlog27 Jul

Kimi K3 by Moonshot now available on Modal

BasetenBlog26 Jul

How we built the new fastest API for GLM-5.2

BasetenBlog23 Jul

How to optimize LLM inference speed and reduce costs in production

ModalBlog15 Jul

Inkling by Thinking Machines now available on Modal

CohereBlog10 Jul

Hardware-Aware, Dynamic Speculative Decoding (DSD)

Showing the newest 41 of 59 posts.