Impressive work!
For comparison, an H100 can do roughly 100-200 tok/s of Muse 30B for raw inference single-thread, going up to low thousands of tok/s with a large number of threads - and I am sure that for the massively-multi-threaded case they can optimize the prover further.
RAND, 8200, StarkWare and SSI alumni raise $20 million to secure AI.
@attestable is betting that zero-knowledge cryptography can provide a new way for companies and governments to verify what happens inside increasingly powerful AI systems.
calcalistech.com/ctechnews/arti…
This is important, and we will provide the technology that will make this happen. The world needs a trustless governance solution that is too cheap to meter!
At the core of our mission is working through how to ensure increasingly powerful AI benefits everyone.
We believe that, at some point in the future, AI acceleration for frontier model development may be so high that the world will need to pace the rate of AI advancement.
We
