Comments (5)
在RTX 4090上复现了这个问题,驱动版本 535.129.03,cuda版本 11.8.89,conda 22.11.1,python 3.10
1、启动bge-reranker-large uuid=12,xinference list无启动模型
2、启动bge-large-zh-v1.5 uuid=12,报错uuid重复
3、启动bge-large-zh-v1.5 uuid=13,xinference list显示模型正常启动,显存被正常占用
from inference.
@bigzws 收到。我这边可以复现,本周发布新版时将修复。原因是xinference list命令目前还没有加入rerank模型的显示。
另外,launch rerank模型后看不到显存占用是正常的,embedding和rerank模型要在真正使用时才会看到显存占用。
from inference.
另外,基于我目前的情况,还有一个问题,dify调用bge-reranker报错,但是在xinference服务中,没有任何报错提示,仅bge-reranker报错,LLM和embedding模型可正常添加到dify
from inference.
dify版本0.5.8
from inference.
@bigzws dify问题请到dify社区咨询
from inference.
Related Issues (20)
- QUESTIONdocker pull error HOT 1
- BUG: Lack of thirdparty.ChatTTS files in built wheels HOT 1
- BUG: missing ChatTTS thirdparty files in docker image HOT 1
- QUESTION:GLM-4V-9B为什么没有4bit量化版本,我看官方性能测试里面是有的
- chatTTS BUG HOT 2
- 可以支持Qwen-Audio这个模型吗 HOT 1
- 无法拉取docker镜像 HOT 1
- BUG: XINFERENCE_MODEL_SRC=huggingface 在中文系统下不生效 HOT 1
- cogvlm2,internvl-chat error
- BUG: Could not start custom registered model: sdxl-turbo HOT 1
- BUG: NCCL error: HOT 11
- Qwen2-7B & Qwen2-72B support context length 128K? HOT 1
- 关于自己注册的模型无法使用vLLM加速的问题。
- BUG:cogvlm2-llama3-chinese-chat-19B model crushed--Expected all tensors to be on the same device HOT 1
- 不支持自定义rerank模型 HOT 1
- Support tools of Qwen2-72B-Instruct HOT 1
- QUESTION HOT 1
- 新版本的xinference,glm4不支持 tools 能力?
- 自行下载的模型如何注册,请给个例子 HOT 1
- 机器上有两张卡,启动一直报错 HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from inference.