Fleek

@xcorat not for long! ⚡️

@fleek Shows how inefficient LLMs truly are!

NVIDIA just dropped benchmarks showing 4-bit inference loses less than 1 point vs BF16 on most tasks. It's not accuracy per request that you should be measuring. It's tasks completed per dollar. And at that metric, 4-bit wins by a landslide. Read the full blog 👇

@OpheliaMystic There are several other components to the stack that will be open-sourced in the coming weeks / months. Stay tuned, and keep an eye out on the repos 👀

@fleek This looks intriguing! The integration of mdspan with CUTLASS layouts could streamline our CUDA workflow significantly. I appreciate the focus on minimizing overhead while enhancing functionality. Excited to check out the complete example! 🚀

1/ Yesterday we announced mdspan-cute: C++23 std::mdspan syntax with CUTLASS cute layouts. One header. Zero overhead. Here's how it works 🧵

8/ Check out the code: github.com/weyl-ai/mdspan… Check out the Proofs: github.com/weyl-ai/mdspan… /end

7/ Layout algebra is formalized in Lean 4. 26 theorems, 0 sorry. Properties extracted to RapidCheck tests. The art/ directory has 23 SVG visualizations - we drew pictures until we understood.

Read the blog: weyl.ai/plan/mdspan-cu… Check out the repo: github.com/weyl-ai/mdspan…

💿 Open Source Release 💿 mdspan-cute: a zero-overhead bridge between C++23 std::mdspan and CUTLASS cute layouts. One header. Swizzled memory. No bank conflicts. Read the blog and check out the repo (links in reply)

@cv_alphas @grok If their broad definition stands, it has implications for other industries including drones, robotics, and more - not just the EVs they claim later in the patent it applies to

@fleek @grok so it’s derivative then

@cv_alphas @grok "Derivative" would mean it's based on prior art. rfl means it IS prior art. Not derived. Identical.

6/ On "bit augmentation": Log/exp is a bijection. Information in = information out. You can't create precision from a reversible transformation. Thermodynamics doesn't allow it.

5/ Quantized RoPE already runs in: → LLaMA → Mistral → Most open source inference stacks This isn't obscure. It's foundational.