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
- Reduce Downtime Up To 50% by Utilizing AI-Ready RAS Features of Intel® Xeon® Processors
- How to Fine-Tune an LLM on Intel® GPUs With Unsloth
- Intel® Xeon® Processors Set the Standard for Vector Search Benchmark Performance
- From Gold Rush to Factory: How to Think About TCO for Enterprise AI
- A Practical Guide to CPU-Optimized LLM Deployment on Intel® Xeon® 6 Processors on AWS.
-
Neural networks news
Intel NN News
- Reduce Downtime Up To 50% by Utilizing AI-Ready RAS Features of Intel® Xeon® Processors
As generative and agentic AI use cases proliferate across nearly every industry, improving the […]
- How to Fine-Tune an LLM on Intel® GPUs With Unsloth
Fine-tuning an LLM doesn’t have to require massive infrastructure. With Unsloth now supporting […]
- Intel® Xeon® Processors Set the Standard for Vector Search Benchmark Performance
In real-world vector search performance tests, Intel® Xeon® server architectures outperform AMD […]
- Reduce Downtime Up To 50% by Utilizing AI-Ready RAS Features of Intel® Xeon® Processors
-