Conner Takehana

introducing chipmunk—a training-free algorithm making ai video generation 3.7x & image gen 1.6x faster! ⚡️ our kernels for column-sparse attention are 9.3x faster than FlashAttention-3 and column-sparse GEMM is 2.5x faster vs. cuBLAS a thread on the GPU kernel optimizations 🧵

with the best team @bfspector , @simran_s_arora , @realDanFu , @HazyResearch

we wrote a blog about TK on M2s: hazyresearch.stanford.edu/blog/2024-11-2…

Happy Thanksgiving! Introducing ThunderMittens for your ThunderKittens, TK kernels for Apple chips! - @AaryanSinghal4 and I

Thankful for TK kernels that now run on Apple hardware - with @CKT_Conner, bringing faster attention and GEMMs to your M2 MacBooks! happy thanksgiving 🍁

Thrilled to be unveiling Thunderkittens 0.1: now with more simplicity, more speed, and more kernels! Had a blast working on this with @bfspector, @simran_s_arora, and folks at @HazyResearch 🚀

but barron, we already have sahil at home, son

we really went from racing hamsters to getting the eth etf approved

Introducing ambientGPT: an open-source and multimodal MacOS foundation model GUI Run GPT-4o and open-source models with full ambient knowledge of your screen. Foundation models have long been confined to the browser. With ambientGPT, your screen context is directly inferred as part of the query, ensuring you never need to explicitly upload context again! Github: github.com/siddrrsh/ambie…

The three presidential candidates are now competing to prove that they can pump your bags more than the other two. We are the new wealthy elite. Newsy Johnson

@kolelee_ quick side quest. gotta get back to shilling shitcoins

The legend himself has made his first post! Give @CKT_Conner a follow if you are into crypto/Distributed ML

@punwaiw @AkshGarg03 @dill_pkl @emilyzsh @ionet you forgot abt their singular RGB gaming PC

(1/5) @CKT_Conner, @dill_pkl, @emilyzsh, and I are excited to introduce Shard - a proof-of-concept for an infinitely scalable distributed system composed of consumer hardware for training and running ML models! Features: - Data + Pipeline Parallel for handling arbitrarily large models - Algorithmic load balancing for throughput optimization - Fault tolerance for unreliable machines

I’m going to tell my kids this was Warren Buffett.

if you saw something like this in ancient times you’d 100% start a religion around it

No words you guys know what’s about to happen….

BREAKING: Legendary mathematician and hedge fund manager Jim Simons has passed away, age 86. His Medallion fund was called "Greatest Money-Making Machine of All Time" and made an annual return of 62% per year from 1988 to 2018 (before fees).

Don't really blame @hosseeb for this to be honest. Its pretty clear the rest of the crypto VCs are following some variation of my due diligence framework. Most don't have @dragonfly_xyz's resources. I have now updated it for future reference.

one of my favorite text exchanges this cycle