time series analytics for vLLM

Go to file

BuildTools ba2a610ac5 Merge branch 'main' of https://github.com/leafspark/vAnalytics		2024-09-21 16:37:04 -07:00
.github	docs: add README.md and initial commit	2024-09-21 16:30:15 -07:00
src	Fix code scanning alert #1 : Uncontrolled command line	2024-09-21 16:35:20 -07:00
.gitignore	docs: add README.md and initial commit	2024-09-21 16:30:15 -07:00
.pre-commit-config.yaml	docs: add README.md and initial commit	2024-09-21 16:30:15 -07:00
CHANGELOG.md	docs: add README.md and initial commit	2024-09-21 16:30:15 -07:00
CODE_OF_CONDUCT.md	docs: add README.md and initial commit	2024-09-21 16:30:15 -07:00
CONTRIBUTING.md	docs: add README.md and initial commit	2024-09-21 16:30:15 -07:00
LICENSE	docs: add README.md and initial commit	2024-09-21 16:30:15 -07:00
README.md	docs: fix shields	2024-09-21 16:36:56 -07:00
SECURITY.md	docs: add README.md and initial commit	2024-09-21 16:30:15 -07:00
requirements.txt	build(deps): update numpy requirement from ~=1.26.4 to ~=2.1.1	2024-09-21 23:31:12 +00:00
setup.py	docs: add README.md and initial commit	2024-09-21 16:30:15 -07:00

README.md

vAnalytics - time series analytics for vLLM

vAnalytics provides a web interface to help easily monitor vLLM instance metrics. It allows users to easily monitor multiple vLLM instances, as well as being easy to setup and configure.

Features

Specify vLLM backends easily using name and host configuration
Uses SQLite for easy database management
Intuitive and includes error handling
Flexible schemas and data plotting using Plotly

Usage

Configure your instances in monitor.py, then use python src/monitor.py. This will start monitoring in a /data folder, where it will store SQLite databases with your model name.

To start the web interface, execute python src/graph.py. The web interface is avaliable at localhost:4412.