Video yรผkleniyor...
Video Yรผklenemedi
๐๐ญ๐ก๐๐ซ๐๐ฎ๐ฆ ๐ก๐๐ฌ ๐ฌ๐ฉ๐จ๐ค๐๐ง ๐ข๐ญ๐ฌ ๐๐ข๐ซ๐ฌ๐ญ ๐ฐ๐จ๐ซ๐! That's right โ we have completed the world's 1st ZKP of a 1B+ param LLM inference, before verifying the proof on Ethereum mainnet (block 19427725) ๐คฏ What did Ethereum say? Learn more in ๐งต
97,181 gรถrรผntรผleme โข 2 yฤฑl รถnce โขvia X (Twitter)
10 Yorum

GPT2-XL is a 1.5B parameter behemoth of an AI model! And to see whether ZKML has finally advanced enough to make proving LLMs feasible at all, we decided to put our proving chops to the test and find out! Oh! It said: "magic", btw <-->

This was no easy task ๐ฅต We had to split GPT2-XL's 48 decoder blocks into 144 sub-blocks, before proving on our massive 1TB memory, 128 core CPU cloud clusters for nearly 90 hours! That means that โ using generic prover systems โ zkLLM overhead is over 1,000,000x!!!

So it's possible โ nice! But the proving overhead is far from acceptable...for now ๐ As we demonstrate in our latest paper, specialization offer 1,000-10,000x speed-ups for ZKML! In fact, we already have some exciting new updates cooking at the bleeding edge ๐๏ธ

In the meantime, check out our blog for what it took to prove a real LLM, why specialization is the future, & the endgame for AI x crypto! Medium blog: Eth block: Follow @ModulusLabs for the latest in ZKML, AI x Crypto, & more ๐ค

Nice, did you use @ezklxyz for the Halo2 proof or write it directly in Halo2?

๐

why is it important to do zkp of LLM inference?

Big congrats @realDanielShorr & team! ๐ฅ

So sick

Are you wrapping the final proof in Groth16? Is there any code/ writeup about that? I am interested in how GKR is being used and how it is getting 'onchain'.

