charles_irl

Karma: 359
Created: 1 year ago

About

Building useful technology out of large neural networks. https://modal.com

Recent Submissions

1. ▲ Cutting inference cold starts by 40x with LP, FUSE, C/R, and CUDA-checkpoint (modal.com) 79 points · 12 hours ago · 18 comments
2. ▲ How to Achieve Serverless GPUs (modal.com) 8 points · 6 days ago · 0 comments
3. ▲ Three types of LLM workloads and how to serve them (modal.com) 75 points · 3 months ago · 5 comments
4. ▲ Host overhead is killing your inference efficiency (modal.com) 3 points · 6 months ago · 0 comments
5. ▲ Quantized Float Exposed (quant.exposed) 2 points · 6 months ago · 1 comment
6. ▲ Against SQL (2021) (scattered-thoughts.net) 82 points · 6 months ago · 77 comments
7. ▲ Length-extension attacks are still a thing (00f.net) 2 points · 6 months ago · 1 comment
8. ▲ The future of Python web services looks GIL-free (blog.baro.dev) 3 points · 7 months ago · 0 comments
9. ▲ Lexical differential highlighting instead of syntax highlighting (wordsandbuttons.online) 2 points · 7 months ago · 0 comments
10. ▲ CReact – JSX for the Cloud (github.com) 1 point · 7 months ago · 0 comments

All submissions on HN · View profile on HN