Today MLCommons® published industry results for their AI training v2.1 benchmark that contained an impressive number of submissions, with over 100 results from a wide array of industry suppliers, with roughly 90% of the entries for commercially available systems, ~10% in preview (not yet commercially available) and a few in “research,” not yet targeting commercial availability at this time. Habana® Gaudi®2 is one of three AI accelerators reporting results, with Nvidia A100 and H100 rounding out the category, with H100 in preview (not available yet).
-
-
Articles récents
- Orchestrating AI for Real Business Value: Google Cloud’s Approach to Scalable Intelligence
- Curious Case of Chain of Thought: Improving CoT Efficiency via Training-Free Steerable Reasoning
- Intel Labs Works with Hugging Face to Deploy Tools for Enhanced LLM Efficiency
- AI’s Next Frontier: Human Collaboration, Data Strategy, and Scale
- Efficient PDF Summarization with CrewAI and Intel® XPU Optimization
-
Neural networks news
Intel NN News
- Orchestrating AI for Real Business Value: Google Cloud’s Approach to Scalable Intelligence
In the race to operationalize AI, success hinges not on hype, but on clarity, customization, and […]
- Curious Case of Chain of Thought: Improving CoT Efficiency via Training-Free Steerable Reasoning
Researchers from the University of Texas at Austin and Intel Labs investigated chain-of-thought […]
- AI’s Next Frontier: Human Collaboration, Data Strategy, and Scale
Ramtin Davanlou, CTO of the Accenture and Intel Partnership, explores what it really takes for […]
- Orchestrating AI for Real Business Value: Google Cloud’s Approach to Scalable Intelligence
-