true love is when they let you use their gpus
HARDWARE
-
Deep Learning’s Legendary Appetite for Compute Resources
By
–
I don't have too too much to add on top of this earlier post on V3 and I think it applies to R1 too (which is the more recent, thinking equivalent). I will say that Deep Learning has a legendary ravenous appetite for compute, like no other algorithm that has ever been developed
-
Cora Computer Reaches 10k Total Signups Milestone
By
–
we passed 10k total signups for @coracomputer
!! -
Stargate $500B infrastructure investment accelerates data center development
By
–
Should Stargate follow through with $500B, it'll be the largest infrastructure spend in history and significantly accelerate the already startling pace of data center development post-ChatGPT. In turn that will significantly accelerate the aforementioned consequences. 13/
-
DeepSeek-R1-distill now on Groq
By
–
NEW : DeepSeek-R1-distill model is now available on groq It performs less than a full o1 but is much faster. * keep in mind that this is not a DeepSeek R1
-
DeepSeek R1 7B: Powerful Reasoning AI on Local Networks
By
–
Here’s deepseek r1 7b (qwen) beaming from my laptop to my phone at 60 tok/s.
— Aaron Ng (@localghost) 25 janvier 2025
Wild that you can serve such powerful reasoning AI models to your whole network with just a few apps. pic.twitter.com/RTHnrjmzRhHere’s deepseek r1 7b (qwen) beaming from my laptop to my phone at 60 tok/s. Wild that you can serve such powerful reasoning AI models to your whole network with just a few apps.
-
HP 1968 Ad: Computer Affordability Under $10,000
By
–
An HP ad from 1968: "Is it possible to get a really good computer for less than $10,000?" v/HP Computer Museum
-
Optimizing AI Apps for iPad and Low RAM Devices
By
–
Some of them take too much ram, i put them there for iPads etc
-
Digital In-Memory Computing Transforms AI Efficiency and Edge Inference
By
–
Revolutionizing AI with Digital In-Memory Computing (D-IMC) D-IMC powers our Metis AIPUs, delivering: Energy efficiency: Less data movement = lower power High throughput: Fast edge AI inference Cost savings: Smaller, smarter chips https://
axelera.ai/blog/how-our-q
uantization-methods-make-the-metis-aipu-highly-efficient-and-accurate
…