May 5, 2025
LLM Inference Speed Benchmarks We measured the prompt processing and text generation speed of different LLMs on 2000+ cloud servers.
Apr 2, 2025
Optimizing Resource Usage of Batch Jobs Seamlessly track the resource usage of e.g. Metaflow steps and find the best value servers for any workload!
Oct 24, 2024
vCPUs in the Real World: Do They Truly Scale? Analyzing empirical data to see if it is enough to choose a cloud instance based solely on the number of vCPUs?
May 28, 2024
Unlocking Cloud Compute Performance All benchmarks are wrong, but some are useful... especially when numerous scenarios and methods are provided.