Skip to content

Hazy Research company blog

Look Ma, No Bubbles: Designing a Low-Latency Megakernel for Llama-1B

hazyresearch.stanford.edu 11 min read

Benjamin Spector* , Jordan Juravsky* , Stuart Sul , Owen Dugan , Dylan Lim , Dan Fu , Simran Arora , Chris Ré

Read on hazyresearch.stanford.edu → Discuss on HN (31) Archived copy

Points: 236
HN comments: 31
Submissions: 1
Cited by: 0 commenters

AI & Machine Learning Systems & Performance 2025

On Hacker News

Submitted	Title on HN	Points	Comments
May 28, 2025	Look Ma, No Bubbles: Designing a Low-Latency Megakernel for Llama-1B by ljosifov	236	31

More from Hazy Research

All 9 posts →

GPUs Go Brrr

20241,104 points263 commentscited by 3AI & Machine Learning details

We bought the whole GPU, so we're damn well going to use the whole GPU

2025504 points110 comments AI & Machine Learning details

From deep to long learning?

2023499 points117 commentscited by 4AI & Machine Learning details

AMD GPUs Go Brrr

2025268 points92 comments AI & Machine Learning details

HipKittens: Fast and furious AMD kernels

2025244 points91 comments AI & Machine Learning details

How to scale LLMs better with an alternative to transformers

2023156 points31 comments AI & Machine Learning details

Related posts from the same era

Statement on US government directive to suspend access to Fable 5 and Mythos 5

Anthropic20263,158 points2,314 commentscited by 11 details

GPT-4o

OpenAI Blog20243,138 points2,366 commentscited by 16 details

Astra can read and write weights to improve Qwen

Rikiya Takehi20262,960 points899 comments details

HackerTube: YouTube built from videos recommended by HN

karpathy20262,889 points642 comments details

Claude Fable 5

Anthropic20262,626 points2,159 commentscited by 10 details

Claude Code is steganographically marking requests

Thereallo20262,445 points750 commentscited by 3 details