Tag: workload optimization
-
Cloud Blog: Scaling high-performance inference cost-effectively
Source URL: https://cloud.google.com/blog/products/ai-machine-learning/gke-inference-gateway-and-quickstart-are-ga/ Source: Cloud Blog Title: Scaling high-performance inference cost-effectively Feedly Summary: At Google Cloud Next 2025, we announced new inference capabilities with GKE Inference Gateway, including support for vLLM on TPUs, Ironwood TPUs, and Anywhere Cache. Our inference solution is based on AI Hypercomputer, a system built on our experience running models like…
-
Hacker News: AI Flame Graphs
Source URL: https://www.brendangregg.com/blog//2024-10-29/ai-flame-graphs.html Source: Hacker News Title: AI Flame Graphs Feedly Summary: Comments AI Summary and Description: Yes **Summary:** The text discusses Intel’s development of a tool called AI Flame Graphs, designed to optimize AI workloads by profiling resource utilization on AI accelerators and GPUs. By visualizing the software stack and identifying inefficiencies, this tool…