Eric Zhang

@lumalabsai prev @suno @meta @ideogram_ai @ibm

[Luma @LumaLabsAI]

Direction goes in. Cinema comes out.

Ray3.2 is here → https://t.co/TuAuFhZDBn

[Eric Zhang @16BitNarwhal]

does anyone climb at movement and wanna refer me 🙏😁

[Krish Shah @KrishRShah]

You can turn your laptop into a trumpet

[Freeman Jiang @freemanjiangg]

the riskiest live demo i’ve ever pulled off:

2000 phones synchronized with light and audio down to the millisecond.

i'll never forget this night.

[Eric Zhang @16BitNarwhal]

apparently this is what flair gives you after a >8hr delay

[Eric Zhang @16BitNarwhal]

when SSSD

[Tanishq Kumar @tanishqkumar07]

I've been working on a new LLM inference algorithm.

It's called Speculative Speculative Decoding (SSD) and it's up to 2x faster than the strongest inference engines in the world.

Collab w/ @tri_dao @avnermay. Details in thread.

[Eric Zhang @16BitNarwhal]

👀

[Delta Institute @DeltaInstitutes]

Join us in welcoming the first cohort of Delta Fellows! 🎉

Congrats to the ~100 amazing researchers and engineers joining the Delta Institute family. We're excited for our fellows to get to know each other through dinners, retreats, and much more!

Our fellows come from diverse backgrounds: undergrads, PhD students, high-frequency trading, big tech, startups, neolabs, frontier labs, and more. What brings them together is their kindness, intellectual curiosity, and intrinsic passion for their field.

https://t.co/mYHDLV2898

[Eric Zhang @16BitNarwhal]

@_rajanagarwal 🔥🔥🔥

[Eric Zhang @16BitNarwhal]

this man is my inspiration

[rajan agarwal @_rajanagarwal]

i don’t usually share when things go wrong

but recently i was researching world models and it went sideways, but i learned a lot

i wrote a new essay about how not to do research https://t.co/tcF9fBOw4L

[Eric Zhang @16BitNarwhal]

first years at wloo just launched this when i walked into the room

[William Cagas @williamcagas]

Think you’re smart? Prove it.

We built the ranked Human Benchmark for uni students.

Try it out --> https://t.co/eBs95D9aie

P.S. Ur absolutely cracked if you can beat my Tower of Hanoi

[Eric Zhang @16BitNarwhal]

fa looking a little different today

[Eric Zhang @16BitNarwhal]

@_krishchopra

[Eric Zhang @16BitNarwhal]

@hamostaf04 happy unc day!!

[Eric Zhang @16BitNarwhal]

the only modal notebook i dislike

[Eric Zhang @16BitNarwhal]

@_krishchopra is this why you couldn't bring your suno backpack home

[Krish Chopra @_krishchopra]

took a break from coding and decided to spontaneously make a song with @16BitNarwhal - check it out!

https://t.co/LTwpDrOCFY

[λux @novasarc01]

detailed paper on LMCache internals just dropped. covers kv-cache optimization, compute/i/o overlap, dynamic offloading, kv-cache connector interface and overall inference infra design. a must-read if you’re into ml systems and inference.

[Eric Zhang @16BitNarwhal]

@vector_tao

[platers @vector_tao]

pushed a change to pytorch that makes cudagraphs 1ms faster. turns out for every module pytorch checks if its in a list. i made it a set and now prod is 5% faster lol