Executing programs inside transformers with exponentially faster inference (percepta.ai) | HN Screenshots

YHacker Newsscreenshots

Screenshot of percepta.ai: Executing programs inside transformers with exponentially faster inference

First screen, captured 7 months ago.

Looks similar

Screenshot of spectrum.ieee.org: “Imprecise” language models are smaller, speedier, and nearly as accurate

“Imprecise” language models are smaller, speedier, and nearly as accurate (spectrum.ieee.org)

281 points by jnord 2 years ago | 149 comments

Screenshot of alperenkeles.com: LLMs could be, but shouldn't be compilers

LLMs could be, but shouldn't be compilers (alperenkeles.com)

104 points by alpaylan 8 months ago | 112 comments

Screenshot of perplexity.vercel.app: Show HN: Fully client-side GPT2 prediction visualizer

Show HN: Fully client-side GPT2 prediction visualizer (perplexity.vercel.app)

140 points by thesephist 3 years ago | 10 comments

Screenshot of blog.onepatchdown.net: Are compilers deterministic?

Are compilers deterministic?(blog.onepatchdown.net)

35 points by fragmede 8 months ago | 38 comments

Screenshot of manifestai.com: Linear transformers are faster after all

Linear transformers are faster after all (manifestai.com)

94 points by JoelEinbinder 2 years ago | 16 comments

Screenshot of lfortran.org: Lfortran: Modern interactive LLVM-based Fortran compiler

Lfortran: Modern interactive LLVM-based Fortran compiler (lfortran.org)

154 points by zaikunzhang 3 years ago | 51 comments