InternLM / lmdeploy

LMDeploy is a toolkit for compressing, deploying, and serving LLMs.
https://lmdeploy.readthedocs.io/en/latest/
Apache License 2.0
4.21k stars 380 forks source link

[Feature] Support for LLaVA-NeXT #1685

Closed deece closed 3 months ago

deece commented 3 months ago

Motivation

A quantising server for LLaVA-NeXT would be very useful.

Related resources

https://github.com/LLaVA-VL/LLaVA-NeXT

Additional context

No response

irexyc commented 3 months ago

We are going to support this model with pytorch backend in this PR.