InternLM / InternLM/lmdeploy

[Feature] 使用v0.10.2版本和vllmv0.10.2镜像部署Llama2-7b|13B,tp=1对比差距很大,是应为是啥原因

Open
#4,174 6 comments 0 reactions 1 assignee Claimed by @lvhan028 View on GitHub
Dominant language
Python
Stars
8.1k
Forks
748
Avg merge
6d 2h
Merged PRs (30d)
54

Description

### Motivation

Image

### Related resources

lmdeploy serve api_server /mnt/data/models/ydyajyA/Llama-2-13b-chat-hf --server-name 0.0.0.0 --server-port 8000 --tp 1 --log-level INFO

use ydyajyA/Llama-2-13b-chat-hf in modelScope

### Additional context

_No response_

Contributor guide

Open the contributing guide

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.