Hacker News Reader

frogfishon Llama 3.1 405B now runs at 969 tokens/s on Cerebras Inference

Genuinely curious and willing to learn: what are the different inference approaches broadly? Is there any difference in the approach between Cerebras and simplismart.ai which claims to be the fastest?

frogfishon Rust-GPU: Making Rust a first-class language and ecosystem for GPU code

Genuinely curious about the last sentence and would like to learn more on the Gentoo approach. Could you please provide a link or a little more details?

frogfishon Build Your Own Text Editor

What I instantly liked is, how literally it starts from scratch and builds a couple of lines at a time.

Can anybody refer to a similar step by step guide to building a compiler?

frogfishon How to crawl a quarter billion webpages in 40 hours (2012)

Previous discussions: with [1] 67 comments, [2] 23 comments.

[1] https://news.ycombinator.com/item?id=4367933 [2] https://news.ycombinator.com/item?id=10865568