Skip to content

Issues: xorbitsai/inference

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

306 Open 483 Closed
306 Open 483 Closed
Author
Filter by author
Label
Filter by label
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Milestones
Filter by milestone
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

BUG: Could not start custom registered model: sdxl-turbo bug Something isn't working gpu
#1620 opened Jun 12, 2024 by majestichou v0.12.1
cogvlm2，internvl-chat error gpu
#1619 opened Jun 12, 2024 by Savid-mask777 v0.12.1
无法拉取docker镜像
#1614 opened Jun 11, 2024 by masktone v0.12.1
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 question Further information is requested
#1609 opened Jun 8, 2024 by gmaimmortal v0.12.1
1
A BUG when use qwen with stream and tools.
#1596 opened Jun 6, 2024 by idiotTest v0.12.1
6
Support for Classification Models like bert-base-chinese in Xinference
#1594 opened Jun 6, 2024 by try-to-fly v0.12.1
glm4 tool calls support
#1592 opened Jun 6, 2024 by wuyiclover v0.12.1
1
3
QUESTION：How are xinference and ragflow linked？ question Further information is requested
#1590 opened Jun 6, 2024 by Alchemistqqqq v0.12.1
CogVLM2使用量化问题 gpu
#1588 opened Jun 5, 2024 by stay-leave v0.12.1
【BUG】安裝一個模型時提示：Server error: 503 - [address=0.0.0.0:30891, pid=146681] No available slot found for the model
#1586 opened Jun 5, 2024 by vball v0.12.1
7
The stream output format is not consistent with the OpenAI standard format.
#1583 opened Jun 4, 2024 by ZhengHui-Z v0.12.1
自定义embedding模型缺少model_id
#1582 opened Jun 4, 2024 by edisonzf2020 v0.12.1
BUG XINFERENCE_MODEL_SRC not work?
#1581 opened Jun 4, 2024 by QiuZiXian v0.12.1
BUG replica=2时，系统报错 gpu
#1580 opened Jun 4, 2024 by allenxcp v0.12.1
1
Install failed: AttributeError: module 'pkgutil' has no attribute 'ImpImporter'. Did you mean: 'zipimporter'?
#1574 opened Jun 1, 2024 by MountainGG v0.12.1
2
BUG Not support multi card when load gguf format gpu
#1570 opened May 31, 2024 by rickywu v0.12.1
1
BUG: model_uri converts symlink in cache to CamelCase case automatically resuling in a wrong path to directory or file bug Something isn't working
#1569 opened May 31, 2024 by vikrantrathore v0.12.1
使用docker运行qwen1.5-chat的时候报错：CUDA error: uncorrectable ECC error encountered gpu question Further information is requested
#1568 opened May 31, 2024 by dannygeek v0.12.1
注册了一个本地模型，然后重启docker后，ui界面上本地模型不见了，重新注册又提示该名字已被注册 question Further information is requested
#1564 opened May 31, 2024 by tao2021 v0.12.1
Integration of Guided Generation Features from vllm into XInference
#1562 opened May 30, 2024 by sunxichen v0.12.1
3
fastGPT调用EmbeddingModel出错后Xinference挂起，其他所有运行模型都不能使用
#1560 opened May 30, 2024 by zhapi1780 v0.12.1
5
模型重新加载的功能 gpu question Further information is requested
#1554 opened May 29, 2024 by yz00000000 v0.12.1
Support headless service name as hostname
#1552 opened May 29, 2024 by thiner v0.12.1
The Chinese username path is incorrectly identified as a unicode character
#1549 opened May 28, 2024 by 1542305589 v0.12.1
1
内网无法启动内置的模型，使用自定义的方式定义了一个yi-vl-chat的模型，运行的时候报错 question Further information is requested
#1545 opened May 26, 2024 by jiaolongxue v0.12.1
2
ProTip! Add no:assignee to see everything that’s not assigned.