Log inSign up
Dango233 profile banner
user avatar

Dango233

@dango233max
Baking open AI system Garnishing open weights github.com/Dango233/
Shenzhen
Joined November 2011
336
Following
952
Followers
RepliesMedia
  • user avatar
    Dango233
    @dango233max
    Jul 6
    I really miss those days when I used to write strange cutout algorithms to express ideas
    user avatar
    gandamu
    @gandamu_ml
    Jul 4
    First animation from integrated PyTTI C++/CUDA port. I used DD style (@dango233max) CLIP cutouts since that's what I already had in the codebase.. and I think that may be good.
    Image
    00:00
  • user avatar
    Dango233
    @dango233max
    May 11
    DS4 is geart! I made a temporary fork with my weekend patches while the PRs are under review - unlock q4 on 192GB MAC - llama.cpp-style raw completions endpoint: enable Pre-filling and custom templates in SillyTaverns etc. Pre-merge convenience fork only :)
    user avatar
    antirez
    @antirez
    May 7
    Welcome to DS4, a specialized inference engine for DeepSeek v4 Flash. github.com/antirez/ds4 This project would have been impossible without the existence of llama.cpp and GGML and the work of @ggerganov and all the other contributors. Thanks!
  • user avatar
    Dango233
    @dango233max
    Jan 2
    值得想沿着这个思路往下走的朋友们想的问题： 这个思路的核心，是微分几何，还是运筹学/系统工程？
    user avatar
    virushuo
    @virushuo
    Jan 2
    昨天我俩讨论了一下这个paper，首先它的突破性和解决问题的漂亮是没问题的。但有意思的地方是： 1 它是从微分几何获得了一个证明，然后找到了解法，还是 先在工程上凑到了一个解法，然后用流型做证明？ 2 沿着这个思路，还有什么可推导的其他用途？
  • user avatar
    Dango233
    @dango233max
    Jan 2
    锐评：挂流形的羊头，卖运筹学的狗肉，论文命名的反向工程，给工程解法找理论爹 千万别被“流形”这个词骗了。说是从流形理论推导的，我敢打赌这绝对是从运筹学“倒着来”的，想从微分几何去理解是南辕北辙。 我工业工程的DNA动了，怪不得这么多人“看不懂”。说是指派问题我的IE同学们是不是能看懂 ？
    user avatar
    alphaXiv
    @askalphaxiv
    Jan 1
    DeepSeek just dropped a banger paper to wrap up 2025 "mHC: Manifold-Constrained Hyper-Connections" Hyper-Connections turn the single residual “highway” in transformers into n parallel lanes, and each layer learns how to shuffle and share signal between lanes. But if each layer
    Image