GateGPT: 56k tokens per second Transformer (KV cache) on FPGA at 80 MHz
twitter.com33 pointsby laxmena11 comments
Loading comments…
Related stories
John Carmack on Fabrice Bellard
twitter.com · 485 points · 247 comments
Ctx, save tokens by loading only the relevant tools
github.com · 3 points · 0 comments
A backdoor in a LinkedIn job offer
roman.pt · 1353 points · 256 comments
Iroh 1.0
iroh.computer · 1276 points · 392 comments
Has anyone replaced Claude/GPT with a local model for daily coding?
1225 points · 517 comments
TinyWind: A pixel pirate sailing game with real wind physics (380k+ kms sailed)
tinywind.io · 915 points · 162 comments