Kernel Optimization

21 posts · 10 sources

+2

AI EngineerYouTube14h

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

AI EngineerYouTube23h

Taming the AI Hardware Cambrian Explosion — Abdul Dakkak, Modular

Two Minute PapersYouTube1w

The Billion Dollar AI Advantage Is Disappearing

AI EngineerYouTube3w

Weight Folding, CUDA Streams, and the Bug That Made My Model Speak Backwards — Filip Makraduli

NVIDIABlog4w

Accelerating Dropless MoE Training in JAX with NVIDIA Transformer Engine

NVIDIABlog2 Sept

The Modern CUDA Toolbox in Practice: A Step-by-Step Optimization Walkthrough

Hugging FaceBlog1 Sept

Introducing @huggingface/kernels: 200+ WebGPU Kernels for Local AI

BasetenBlog29 Aug

Agentic kernels in production

GoogleBlog13 Aug

HeyGen x Google Cloud: Bringing Avatar IV to TPUs- Google Developers Blog

CursorBlog4 Aug

Mixture-of-Kittens: our open-source MoE megakernel for NVL72s

MetaBlog3 Aug

GEM Training: How Meta Doubled the Efficiency of Its LLM-Scale Ads Foundation Model

Fireworks AIBlog10 Jul

Optimizing MiniMax M3 Sparse Attention on NVIDIA Blackwell

NVIDIABlog24 Jun

Accelerating BEV Pooling on NVIDIA GPUs for Physical AI Applications

Together AIBlog2 Jun

Serving MiniMax-M3 for efficient inference: Unlocking 1M-Token Context and Multimodality Without Regrets

NVIDIABlog27 May

Extract More Kernel Performance with NVIDIA CompileIQ Auto-Tuning

Together AIBlog19 May

Benchmarking inference at scale: coding agents

CursorBlog14 Apr

Speeding up GPU kernels by 38% with a multi-agent system

CursorBlog6 Apr

Better MoE model inference with warp decode

MetaBlog2 Apr

KernelEvolve: How Meta’s Ranking Engineer Agent Optimizes AI Infrastructure

Together AIBlog17 Mar

Mamba-3