Register and share your invite link to earn from video plays and referrals.

Suvaditya Mukherjee
@halcyonrayes
920 Following    2.2K Followers
i asked claude to implement trellis.2 fully in cuda c++, and it is 5.3x faster than the original pytorch implementation 🚀 surprisingly, the glb-export function was the bottleneck, not the neural net itself. moving exporting to the gpu gave more gains than anything else. - zero python runtime, all in c++ ⚡️ - cost 💵 ? ~$7 on claude and ~$60 on compute for testing on h200s through @huggingface jobs - it still gave 2.2x better perf while being bitwise identical 🎯 the code is open-sourced for use here -- use it as a source for your agent to optimize your models, or utilize it directly. happy hacking! 🤗
Show more
world models are coming faster than we realize 🌎 so i wrote a blog that tells you what they are, what the state of the art looks like, what the eval axes look like, and how you can stay updated 🚀 check it out here 🤗 --
Show more
3d is not one single format. images have pixels, but what about 3d? i wrote a blog that takes you on an interactive journey of what the current 3d ecosystem looks like, and why there's never been a better time to start 🚀 check it out here -- 🤗
Show more
bring your blender 3d worlds to the 🤗 hub! i made a skill here that will use @huggingface cli to push your agent traces to the hub: simply tell your agent after your world is ready, to use this skill all the worlds are available openly on this public dataset: go forth and render!
Show more