How to make LLMs go fast (vgel.me)

Screenshot of vgel.me: How to make LLMs go fast

First screen, captured 2 years ago.

Looks similar

Screenshot of vgel.me: I made a transformer to predict a simple sequence manually

I made a transformer to predict a simple sequence manually (vgel.me)

314 points by lukastyrychtr 3 years ago | 80 comments

Screenshot of cerebras.net: GigaGPT: GPT-3 sized models in 565 lines of code

GigaGPT: GPT-3 sized models in 565 lines of code (cerebras.net)

199 points by georgehill 2 years ago | 60 comments

Screenshot of vgel.me: Writing a C compiler in 500 lines of Python

Writing a C compiler in 500 lines of Python (vgel.me)

454 points by vgel 3 years ago | 142 comments

Blog post by vgel describing the design and architecture of a small C compiler written in about 500 lines of Python.

compilers c python webassembly

Screenshot of simonwillison.net: Understanding GPT tokenizers

Understanding GPT tokenizers (simonwillison.net)

380 points by simonw 3 years ago | 110 comments

Simon Willison blog post explaining how GPT tokenizers convert text to integer tokens, with an Observable notebook tool for encoding, decoding and searching tokens.

tokenizers gpt openai llm

Screenshot of rushter.com: Oh My Zsh adds bloat

Oh My Zsh adds bloat (rushter.com)

285 points by fla 9 months ago | 255 comments

Screenshot of vgel.me: Writing a C compiler in 500 lines of Python (2023)

Writing a C compiler in 500 lines of Python (2023)(vgel.me)

231 points by ofou 1 year ago | 74 comments

Looks similar

I made a transformer to predict a simple sequence manually(vgel.me)

GigaGPT: GPT-3 sized models in 565 lines of code(cerebras.net)

Writing a C compiler in 500 lines of Python(vgel.me)

Understanding GPT tokenizers(simonwillison.net)

Oh My Zsh adds bloat(rushter.com)