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

233 Open 895 Closed
233 Open 895 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
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

启动模型replica参数貌似只能部署到不同卡上，replica大于卡数将会报错 gpu
#2093 opened Aug 15, 2024 by mote0302
1 of 3 tasks
v0.14.0
2
cosyvoice 基于指令的声音合成报错 TypeError: speech() got an unexpected keyword argument 'instruct_text'
#2091 opened Aug 15, 2024 by reinforceli
1 of 3 tasks
v0.14.0
1
to support Qwen2-Audio model feature
#2090 opened Aug 15, 2024 by jaffe-fly v0.14.0
1
internlm2.5-7B-chat& internlm2.5-7B-chat-1M can't run in vllm gptq-4Int gpu
#2089 opened Aug 14, 2024 by soulzzz
1 of 3 tasks
v0.14.0
3
视频输出格式不能修改成url，无法生效。本地也未见保存的视频。
#2088 opened Aug 14, 2024 by Modas-Li
1 of 3 tasks
v0.14.0
1
v0.14.1.post1 版本启动 Kolors-diffusers 模型报错
#2087 opened Aug 14, 2024 by Valdanitooooo v0.14.0
2
无法启动FLUX gpu
#2085 opened Aug 14, 2024 by Minamiyama
1 of 3 tasks
v0.14.0
1
embedding模型在WebUI中无法部署 gpu
#2083 opened Aug 14, 2024 by YaungT
1 of 3 tasks
v0.14.0
3
容器启动xinference和openwebui发生冲突
#2078 opened Aug 13, 2024 by ZJU-lishuang
1 of 3 tasks
v0.14.0
5
Llama 3.1 405B fp16 Support in Distributed Mode feature gpu
#2077 opened Aug 13, 2024 by allenzhangtju v0.14.0
1
gte-Qwen2没有支持fp16推理
#2076 opened Aug 13, 2024 by Zzzz1111
1 of 3 tasks
v0.14.0
10
希望SenseVoiceSmall支持传入额外的参数 feature
#2075 opened Aug 13, 2024 by leslie2046 v0.14.0
2
[feature request] Support inference for the cogvlm2-video-llama3-chat model feature help wanted Extra attention is needed
#2073 opened Aug 13, 2024 by lordk911 v0.14.0
[feature request] MiniCPM-2B-sft-bf16 support vllm inference feature
#2070 opened Aug 12, 2024 by bao21987 v0.14.0
1
Could not run qwen2-moe-instruct-gptq-Int4 gpu
#2066 opened Aug 12, 2024 by wingtch
1 of 3 tasks
v0.14.0
2
set XINFERENCE_HOME="f:/xinference"，这个set后的home不起作用。
#2065 opened Aug 11, 2024 by yourengod
1 of 3 tasks
v0.14.0
1
ConnectionRefusedError: [WinError 10061] gpu
#2064 opened Aug 11, 2024 by YinyiE
1 of 3 tasks
v0.14.0
拉取阿里镜像失败，拉取其他的镜像也失败。
#2062 opened Aug 10, 2024 by yibohub
1 of 3 tasks
v0.14.0
jina-reranker-v2报错 gpu
#2060 opened Aug 10, 2024 by leslie2046
1 of 3 tasks
v0.14.0
1
Xinfernece==0.14报错，笔记本i5核显启动服务报错 RuntimeError: Cluster is not available after multiple attempts
#2058 opened Aug 9, 2024 by YiKangMo
1 of 3 tasks
v0.14.0
1
流式处理结束标识不应该和回复内容合并
#2054 opened Aug 9, 2024 by lizt666888
3 tasks
v0.14.0
4
使用xinference自带聊天页面与大模型交流，特别卡
#2052 opened Aug 9, 2024 by lm970585581
1 of 3 tasks
v0.14.0
4
xprobe/xinference:v0.14.0.post1-cpu 加载 glm-4-9b-chat.Q4_K.gguf 报错：failed to load model
#2051 opened Aug 9, 2024 by Laremn
1 of 3 tasks
v0.14.0
2
Support tool calling For Llama 3.1 gpu
#2045 opened Aug 8, 2024 by ruifengma
1 of 3 tasks
v0.14.0
@codingl2k1
1
新版本启动v0.14.0.post1启动sdxl-turbo失败（猜测是代码笔误：text2iamge 应为 text2image） gpu
#2044 opened Aug 8, 2024 by nikelius
1 of 3 tasks
v0.14.0
3
ProTip! no:milestone will show everything without a milestone.