Dhaval Javia

@notdhavaljavia

AWS Solutions Architect 🏫 Coder😍, Gamer🤩, Introvert🥳, Gym boi💪 and not so easy to understand. Marvel + Batman Fan. Next billionaire on the way.

California, USA

Born November 24

Joined May 2014

486 Following

73 Followers

Replies Reposts Media

Dhaval Javia
@notdhavaljavia
Oct 21
semi closed source? half open source? grey source?
Kush Patel
@thepatelkush
Oct 21
What will be next to open source?
Dhaval Javia
@notdhavaljavia
Oct 16
dafaq? OSS is moving so fast I can't even catch up. if this work, this really is a game changer for smaller models 🤯
Tom Greenwald
@tomgreenwald
Oct 15
We made open models run over 2x faster than Ollama, without any new hardware Introducing Magnitude, an open source inference engine that runs open models as fast as your hardware allows. It tunes its kernels on your machine to find the fastest way to run each model Works on
Dhaval Javia
@notdhavaljavia
Oct 15
That too on some bread pieces and normal food vs gigawatt of electricity
GitHub Projects Community
@GithubProjects
Oct 15
Anthropic, with the help of Claude, spent five months building a replacement for Git, while Linus Torvalds built Git single-handedly in just 10 days.
Dhaval Javia
@notdhavaljavia
Oct 14
want to try this but veryyl clearly mentioned catch. this is the important part that almost nobody talks about. we want to improve oss, but at the same time, knowing limitations helps
Niklas
@niklaslenz_ai
Oct 13
Finally we have it: Strata against llama.cpp on my RTX 5090. Same model file, same prompt. Strata wrote this city in 28.8 s, llama.cpp needed 104.2 s. The model is Qwen3.8-Flash-Next. It doesn't fit in 32 GB, so part of it sits in system RAM. Strata with MTP writes 204 tok/s,
00:00
Dhaval Javia
@notdhavaljavia
Oct 8
goated series after arrow...spent teenage years building this memories. core memories
trix
@trixcuh
Oct 7
first 4 seasons of this show will never be replicated btw
Quote
Blaze Binges
@BlazeBinges
Oct 7
12 years ago today, The Flash premiered on The CW.