num5

Founding Machine Learning Engineer | Making AI practical, reliable, and scalable | LLMs & generative AI

[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.

[num5 @num5_r]

@MainzOnX @ChristosArgyrop 💯💯

[num5 @num5_r]

@hiiinternet Dmed

[num5 @num5_r]

@christinaingoog Congrats!!

[num5 @num5_r]

@elliotarledge Wohoo!!

[num5 @num5_r]

@_DoAnythingNow @ingowoo exactly!!😂

[num5 @num5_r]

@ingowoo savage xdd

[num5 @num5_r]

@ThomasEccel yeah, your website is also down coz of cloudfare

[num5 @num5_r]

@sadernoheart Thank you so much!!! Means a lot

[num5 @num5_r]

@LetMeCodeee Cpp

[num5 @num5_r]

@elsaprofitable Solo dates are always life changing and teaches a lot about ourselves.

[num5 @num5_r]

@iamgrigorev waiting for it !!

[num5 @num5_r]

@hazhubble skip the resume filters. set a real challenge your team is working on and see who shows up hungry to LEARN and DELIVER, even if their background isn’t perfect. those are the builders worth betting on.

[num5 @num5_r]

@elliotarledge @luminal_ai Which virtual gpus do u use for running cuda scripts?

[num5 @num5_r]

@hackwithzach @hthieblot This is something I have been searching for a while now. Thanks a lot!!

[num5 @num5_r]

@hackwithzach @hthieblot Where can I find these hackathons to become one?

[num5 @num5_r]

@iifoundanna @mirandanover 💯💯

[num5 @num5_r]

@ZeetwoZ2 @faker That’s so crazy !!🥳🥳

[num5 @num5_r]

@boltdotnew You need more users or you need more data to train?🤔

[num5 @num5_r]

@saurabhalonee How are you managing time with these many things goin o?