llama3 70b
using vllm
on an h200
HARDWARE
-
Why no real-time voice AI conversations yet despite GPU advances
By
–
crazy that in 2025 i can converse in 1000 tokens/sec on my single GPU machine with AI that’s world-class at math and programming but i still have to type. i can’t speak to it, at least not in low-enough latency to carry a conversation we don’t have this tech yet. why not?
-
Small Language Models: Superior Future of Agentic AI
By
–
1. Small Language Models are the Future of Agentic AI This position paper argues that small language models (SLMs), defined as those runnable on consumer-grade hardware, are not only sufficient but superior for many agentic AI applications.
-
IBM Targets 200 Logical Qubits by 2029 in Quantum Race
By
–
L’informatique quantique sort enfin du laboratoire.
— VISION IA (@vision_ia) 6 juillet 2025
IBM promet 200 qubits logiques d’ici 2029, assez pour bousculer l’industrie.
Correction d’erreur divisée par 10. Applications commerciales en ligne de mire.
La course commence vraiment maintenant pic.twitter.com/X8zG5AY3FBL’informatique quantique sort enfin du laboratoire. IBM promet 200 qubits logiques d’ici 2029, assez pour bousculer l’industrie. Correction d’erreur divisée par 10. Applications commerciales en ligne de mire. La course commence vraiment maintenant
-
Quantum Supremacy: AI, Data Science and Computing Technologies
By
–
Quantum Supremacy! #BigData #Analytics #DataScience #AI #MachineLearning #IoT #IIoT #PyTorch #Python #RStats #TensorFlow #Java #JavaScript #ReactJS #GoLang #CloudComputing #Serverless #DataScientist #Linux #Books #Programming #Coding #100DaysofCode https://
geni.us/Quantum-Suprem
acy
… -
Accelerating Matrix Multiplication with NVIDIA cuBLAS
By
–
Boosting Matrix Multiplication Speed with NVIDIA cuBLAS! #BigData #Analytics #DataScience #AI #MachineLearning #IoT #IIoT #PyTorch #Python #RStats #TensorFlow #Java #JavaScript #ReactJS #GoLang #CloudComputing #Serverless #DataScientist #Linux #Mathematics #Programming #Coding
-
NVIDIA cuDNN Accelerates Transformer Performance on GPU
By
–
Accelerating Transformers with NVIDIA cuDNN! cuDNN: Math Turbocharged on GPU for Accelerating Transformers Like You've Never Seen Before! #BigData #Analytics #AI #MachineLearning #DataScience #IoT #IIoT #Python #RStats #TensorFlow #JavaScript #ReactJS #CloudComputing #Serverless
-
MIT’s Imaging Breakthrough Enables Humanoid Robots Vision
By
–
Humanoid robots could soon see through walls with MIT’s new imaging breakthrough https://
search.app/PA6m9 #imaging #MIT #Robotics #robots #cobot #humanoid #robotech #robotgirl #technology #TechRevolution #tech #Engineering @lexfridman @KirkDBorne @Ronald_vanLoon @erikbryn -
Being a Computer: Electricity and Cooling Requirements
By
–
Ah, to be a computer. All you need is electricity and cooling.
-
Google Willow Quantum Computer Outpaces Supercomputers by Trillion Years
By
–
Un calcul que Willow (ordinateur quantique) fait en 5 minutes… demanderait 10²⁵ ans à notre meilleur supercalculateur.
— VISION IA (@vision_ia) 5 juillet 2025
Soit mille milliards de fois l’âge de l’univers.
La vraie révolution va être quantique + IA.
Êtes-vous prêts ? pic.twitter.com/lBujonFlkjUn calcul que Willow (ordinateur quantique) fait en 5 minutes… demanderait 10²⁵ ans à notre meilleur supercalculateur. Soit mille milliards de fois l’âge de l’univers. La vraie révolution va être quantique + IA.
Êtes-vous prêts ?