djl-serving
djl-serving copied to clipboard
Add benchmark results or link to key features section
Description
The main project page has a list of key features, specifically interested about performance:
- Performance - DJL serving running multithreading inference in a single JVM. Our benchmark shows DJL serving has higher throughput than most C++ model servers on the market.
I could not find any link to the results in the project , or the website https://docs.djl.ai/. Is it possible to add more information about the benchmark?
Will this change the current api? How? No, this is mainly about documentation.
Who will benefit from this enhancement? Users/Developers that are interested in choosing DJL vs other model serving options
References
N/A