leafspark
/
vAnalytics
mirror of https://github.com/leafspark/vAnalytics.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
time series analytics for vLLM
19 Commits 7 Branches 1 Tag 133 KiB
Python 90.3%
HTML 9.1%
Batchfile 0.6%
Go to file
leafspark 82309b5ccf
ci: update artifact upload version 		2025-02-13 17:41:58 -08:00
.github ci: update artifact upload version 2025-02-13 17:41:58 -08:00
.idea feat(config): add configuration options 2024-09-22 09:31:12 -07:00
src feat(config): add configuration options 2024-09-22 09:31:12 -07:00
templates fix: add template to code 2024-09-23 21:49:37 -07:00
.env.example feat(config): add configuration options 2024-09-22 09:31:12 -07:00
.gitignore fix: add template to code 2024-09-23 21:49:37 -07:00
.pre-commit-config.yaml docs: add README.md and initial commit 2024-09-21 16:30:15 -07:00
CHANGELOG.md docs: update changelog to v1.0.0 2024-09-21 16:47:14 -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
models.json.example feat(models): load models from JSON configuration 2024-09-21 16:45:48 -07:00
requirements.txt build(deps): update uvicorn requirement from ~=0.30.6 to ~=0.34.0 2024-12-15 22:47:56 +00:00
run.bat feat(config): add configuration options 2024-09-22 09:31:12 -07:00
setup.py feat(models): load models from JSON configuration 2024-09-21 16:45:48 -07:00

README.md

vAnalytics - time series analytics for vLLM

GitHub release GitHub last commit CI/CD Status

Powered by vLLM GitHub top language Platform Compatibility GitHub license

GitHub stars GitHub forks GitHub release (latest by date) GitHub repo size Lines of Code

Code Style: Black Issues PRs Welcome

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.