it works!!! inferencing bf16 405-base with shallowslow on a @PrimeIntellect 16x H100 cluster over 100Gbe https://t.co/8fIn0wJboD
same thread: 1863101058664554854
cited on: llama-3-1-405b-base
Reproduced against link rot, credited and linked to its original. Yours and you’d rather it weren’t here? Open an issue.