It will be amazing when we have robots that can actually help build stuff like this that we dreamed up with AI.
AI HARDWARE
-
MobileDiffusion enables rapid on-device text-to-image generation
By
–
Check out MobileDiffusion’s potential for rapid text-to-image on-device in testing, shown below: pic.twitter.com/33Ng2it3oF
— Google AI (@GoogleAI) 1 février 2024Check out MobileDiffusion’s potential for rapid text-to-image on-device in testing, shown below:
-
AI Chip Demo Limited Details Released
By
–
not sure – don't see any more specifics. i guess because it's just a demo for their chip
-
Mixtral 8×7 Achieves 488 Tokens Per Second on Groq Hardware
By
–
wow, mixtral 8×7 can hit ~488 tok/s using groqchat's custom chips. realtime analysis or nested llm calls become way more feasible at these speeds
— Aaron Ng (@localghost) 1 février 2024
whole responses in about a second: pic.twitter.com/wv8jX4Uj93wow, mixtral 8×7 can hit ~488 tok/s using groqchat's custom chips. realtime analysis or nested llm calls become way more feasible at these speeds whole responses in about a second:
-
MobileDiffusion Enables Sub-Second On-Device Text-to-Image Generation
By
–
Introducing MobileDiffusion, a novel approach with the potential for rapid (sub-second) text-to-image generation on-device. An efficient latent diffusion model with a comparably small model size, it is well suited for mobile deployment. Learn more →
https://
goo.gle/3vWqE5J -
Tenstorrent Open Sources TT-Metalium Kernel Software Stack
By
–
We're excited to announce that we have open sourced our kernel-level software stack, TT-Metalium. @ojoyoshida sat down with @DavidBennett__ and #tenstorrent fellow Jasmina Vasiljevic to talk #opensource, #software and our Grayskull DevKit https://
ojoyoshidareport.com/if-nvidia-is-a
i-hardwares-goliath-wheres-david/
… -
Singtel Builds Energy-Efficient AI Data Centers with NVIDIA Hopper
By
–
Singtel, a leading communications service provider, is building energy-efficient data centers across Southeast Asia accelerated with NVIDIA Hopper architecture #GPUs and NVIDIA AI reference architectures, serving as sovereign #AI factories. Learn more: https://
nvda.ws/3ueDb3J -
Co-Designing Model Architectures with Hardware
By
–
The Case for Co-Designing Model Architectures with Hardware Anthony et al.: https://
arxiv.org/abs/2401.14489 #ArtificialIntelligence #DeepLearning #MachineLearning -
Tenstorrent Grayskull Devkits Launch with Fellow Jasmina Vasiljevic
By
–
@IanCutress sits down with #tenstorrent Fellow Jasmina Vasiljevic to talk about our soon to be released Grayskull Devkits. Find out more @ http://
tenstorrent.com/cards -
Neuralink brain chip, Bard video summaries, Tencent LLM advances
By
–
Top stories in AI today: -Neuralink places first brain chip implant in human
-Yelp launches new AI features
-Summarize a YouTube video or podcast using Bard
-Tencent details multimodal LLM advances
-6 new AI tools & 4 new AI jobs Read more: http://
therundown.ai/p/neuralinks-t
elepathic-human-milestone
…