You can literally inference LLaMA. And that 192GB in the new Mac Studio is way more than enough to go beyond the 13B param model.
AI HARDWARE
-
Apple CPU gains 20% boost for machine learning applications
By
–
So I know everyone loves to stare down the GPUs here but like a 20% CPU bump on the new Apple CPU is pretty impressive given how much you can do on a CPU these days for ML
-
NVIDIA’s Accelerated Computing Powers Generative AI Era
By
–
We took center stage at #COMPUTEX2023. Our CEO Jensen Huang’s opening keynote showed how NVIDIA’s accelerated computing platform and partner ecosystem are powering the new era of #generativeAI and industrial digitalization. Watch the highlights.
-
AR Headset Evolution: Pricing Strategy and Lightweight Glasses Timeline
By
–
This should be viewed as the start of a product evolution. The rumoured price of the headset would place it into a niche segment. A lower cost version expected next year. The lightweight glasses are not expected until 25/26 or even 27 & I predict that these will be the
-
Apple Introduces New LLM, Headset, and AI-Powered Mac Computers
By
–
apple llm headset
some new macs
lots of AI AI AI generative AI -
Face ID Fails to Recognize Woman Drinking Wine
By
–
Weird that Face ID can’t recognize me while I’m drinking a glass of wine, which is like an extremely recognizable look for me.
-
L’IA intégrée aux wearables dans un an
By
–
Over the next year, we’ll see AI integrated into wearables like this, and people will wonder how they ever lived without it. pic.twitter.com/gyGeEaJZ6o
— AI Breakfast (@AiBreakfast) 4 juin 2023Over the next year, we’ll see AI integrated into wearables like this, and people will wonder how they ever lived without it.
-
Groq Spotlight: AI Inference Discussion Recording Available Now
By
–
If you missed our #GroqSpotlight: Quenching AI Thirst with Inference last week, view the recording for insights from our #LLM discussion. https://
youtube.com/live/YiYwn4b4K
jc?feature=share
… -
Nvidia surge powers TL20 index to sixty-five percent gain
By
–
Nvidia’s surge, and its knock-on effect on Arista Networks and others, has powered the TL20 to a sixty-five percent gain this year, trouncing benchmarks. Better investing comes from knowing tech companies. $NVDA $ANET https://
thetechnologyletter.com/tl20 #investing #stocks -
Groq’s Compiler Approach Keeps Pace with LLM Innovation
By
–
Groq's generalizable compiler and software-defined hardware approach is keeping up with the rapid pace of LLM innovation–something that traditional kernel-based approaches struggle with. We're thrilled to have Gazi Naveed Ahmed on our team to as we continue to innovate. #hiring pic.twitter.com/o4GXtIk17A
— Groq Inc (@GroqInc) 2 juin 2023Groq's generalizable compiler and software-defined hardware approach is keeping up with the rapid pace of LLM innovation–something that traditional kernel-based approaches struggle with. We're thrilled to have Gazi Naveed Ahmed on our team to as we continue to innovate. #hiring