Comments (4)
Ok after doing a second try by removing the vllm from the git it started to work now but UI error is not elimited it still throws an error:
Xinference ui is not built at expected directory: /home/projects/insan_inference/.venv/lib/python3.11/site-packages/xinference/web/ui/build/
To resolve this warning, navigate to /home/projects/insan_inference/.venv/lib/python3.11/site-packages/xinference/web/ui/
And build the Xinference ui by running "npm run build"
warnings.warn(
from inference.
@vikrantrathore Could you paste out your command that you pip install from git?
from inference.
The error is through poetry which uses pip behind. The command is poetry add git+https://github.com/xorbitsai/inference
within a local project.
Once the installation fails at installing xinference, I can go activate the venv by poetry shell
and then install using pip install git+https://github.com/xorbitsai/inference
. It works, but then there is an error of Web UI which is using npm and need to run
npm install
npm run build
This will build the UI. Also vllm used is 0.4.3 and wanted to try 0.5.0 from the git given it supports gemma-2 9B and 27B but couldn't do it due to other dependencies.
Also sglang support gemma-it but when I use sglang worker for gemma-it model it throws an error model not supported so was trying to install it from git directly to see if can use gemma-it with sglang.
from inference.
It seems the error still persist when I try to install it from local directory like poetry add -e ../inference/.["all"]
, probably need to test more extensively with poetry.
from inference.
Related Issues (20)
- 'system_message' is undefined HOT 5
- 升级到0.13.1后局域网访问时要求用户登录 HOT 6
- 调用rerank接口,返回的结果中,results.document 字段返回值都是空 HOT 1
- chatglm3 failed to load model:gguf_init_from_file: invalid magic characters 'V'
- support MInference in feature HOT 1
- 建议能支持一张卡加载多个模型 HOT 1
- Upgrade vllm and sglang to new version and support gemma model correctly HOT 2
- 注册自定义模型后,测试页面不可用 HOT 1
- docker启动时报错,详情见具体异常 HOT 2
- Both `max_new_tokens` (=512) and `max_length`(=518) seem to have been set. `max_new_tokens` will take precedence. Please refer to the documentation for more information. HOT 2
- [ maybe a bug ] Occasional exceptions occurred when reasoning with the mlx model yi-1.5-9b-chat HOT 1
- Failed start when base image from pytorch/pytorch:2.1.2-cuda12.1-cudnn8-devel to vllm/vllm-openai:latest HOT 3
- 支持IPU加速吗? HOT 2
- xinference微调模型的支持
- Qwen1.5-14b-chat-gptq-int4 推理速度
- Failed to do inference with latest GLM-4 chat 9b model HOT 2
- v1/completions接口无法使用,返回空字符串 HOT 1
- 显示启动模型失败,load失败 HOT 1
- Failed to register model, Invalid model URI D:/Pretrainedmodels3/ZhipuAI/chat4/glm-4-9b-chat.
- 建议新增对图embedding模型的
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.