Spare Cores

We benchmarked 2k+ cloud servers for LLM inference speed (prompt processing and text generation) using models ranging from 135M to 70B parameters! 🤖

Read tech details, use our open-source tools, learn from the results at https://sparecores.com/article/llm-inference-speed

#llm #large_language_models #benchmark #cloud

Ever wondered how much CPU, memory, GPU, disk, or network traffic your #metaflow steps use and how to optimize resource allocation? The open-source resource-tracker Python package does that (and more) with seamless Metaflow integration! Read more at https://sparecores.com/article/metaflow-resource-tracker 🚀

We are proud to share our participation in the NVIDIA Inception Program, which will help us boost and extend our benchmarking capabilities, especially when it comes to ML/AI workloads 🎉

https://sparecores.com/article/nvidia-inception

#NVIDIAInception