https://github.com/kvablack/LLaVA-server

https://github.com/kvablack/LLaVA-server

Last synced: 16 days ago
JSON representation

• Host: GitHub
• URL: https://github.com/kvablack/LLaVA-server
• Owner: kvablack
• License: mit
• Created: 2023-04-30T01:21:30.000Z (about 1 year ago)
• Default Branch: main
• Last Pushed: 2023-10-20T18:09:03.000Z (8 months ago)
• Last Synced: 2024-04-18T05:39:14.000Z (2 months ago)
• Language: Python
• Size: 373 KB
• Stars: 15
• Watchers: 1
• Forks: 5
• Open Issues: 3
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Lists

• awesome-stars - kvablack/LLaVA-server - (Python)

README

        
# LLaVA-server

Serves LLaVA inference using an HTTP server. Supports batched inference and caches the embeddings for each image in order to produce multiple responses per image more efficiently.

## Usage

```bash

gunicorn "app:create_app()"

```

You must modify `gunicorn.conf.py` to change the number of GPUs.