Skip to content

Issues: xorbitsai/inference

Beta
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

171 Open 1,823 Closed
171 Open 1,823 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

llama 加载gguf模型报错 gpu
#3345 opened Apr 27, 2025 by pkusub
1 of 3 tasks
v1.x
3
[NEW MODEL][ASR]Kimi-Audio feature new model
#3341 opened Apr 26, 2025 by Minamiyama v1.x
无法下载国内xinference:v1.4.1镜像
#3339 opened Apr 25, 2025 by wwloo2018
1 of 3 tasks
v1.x
1
builtin model not found: xinference launch --model-engine MLX --model-name gemma-3-it --size-in-billions 4 --model-format mlx --quantization fp16 # or quantization=bf16 gpu
#3336 opened Apr 25, 2025 by bugfyi
3 tasks
v1.x
1
[NEW MODEL][VL]Skywork-R1V2 feature new model
#3334 opened Apr 24, 2025 by Minamiyama v1.x
API端口是多少
#3333 opened Apr 24, 2025 by fabianlv v1.x
5
使用xllamacpp运行deepseek-r1-distill-qwen gguf模型提示ggml_cuda_init: failed to initialize ROCm: no ROCm-capable device is detected，模型加载到了运行内存中 gpu
#3332 opened Apr 24, 2025 by githust66
1 of 3 tasks
v1.x
3
InternVL3-14B模型报错can only concatenate str (not "list") to str gpu
#3330 opened Apr 24, 2025 by zyh3826
1 of 3 tasks
v1.x
1
Got an error when try to launch GLM4 model in docker container gpu
#3329 opened Apr 24, 2025 by HDhuangdi
1 of 3 tasks
v1.x
1
希望加入能自定义elapsed time时间的功能 feature
#3328 opened Apr 23, 2025 by goodmaney v1.x
1
pip install "xinference[all]" 报错 error: subprocess-exited-with-error gpu
#3327 opened Apr 23, 2025 by qiulang
1 of 3 tasks
v1.x
10
Qwen2.5 Omni部署有问题
#3323 opened Apr 23, 2025 by zswodegit
3 tasks
v1.x
32
部署QwQ模型出现KeyError: 'text' gpu
#3322 opened Apr 23, 2025 by cl12191718
1 of 3 tasks
v1.x
6
LLM回复有时是截断的，但是max_tokens的设置设置为很大， 这个参数难道不是指定LLM返回内容的token数吗，为什么设置了很大还是只输出了一小部分的内容呢？可以有人帮忙看下嘛谢谢！ gpu
#3319 opened Apr 22, 2025 by azhe1234
1 of 3 tasks
v1.x
1
Xinference support jina-reranker-m0 feature
#3316 opened Apr 22, 2025 by doutianye v1.x
1
PyTorch 存在远程代码执行漏洞（CVE-2025-32434） gpu
#3314 opened Apr 22, 2025 by luofeng0603 v1.x
1
无法正常启动模型
#3312 opened Apr 21, 2025 by GXKIM
1 of 3 tasks
v1.x
7
新老版本依赖问题
#3310 opened Apr 21, 2025 by zx1003 v1.x
5
QWQ-32B 支持添加函数调用 feature
#3309 opened Apr 21, 2025 by suntao2015005848 v1.x
@amumu96
Docker下模型虚拟空间--qwen2.5-omni报错 gpu
#3299 opened Apr 21, 2025 by VITA-Alchemy
1 of 3 tasks
v1.x
7
qwen2.5-omni启动报错 gpu
#3295 opened Apr 19, 2025 by wang5766171
1 of 3 tasks
v1.x
6
qwen2.5-instruct模型响应回答很缓慢 gpu
#3292 opened Apr 19, 2025 by leo-bot
1 of 3 tasks
v1.x
2
使用自定义模型，启动之后发起聊天会话失败 gpu stale
#3291 opened Apr 19, 2025 by leo-bot
1 of 3 tasks
v1.x
2
Docker启动webui报错
#3290 opened Apr 19, 2025 by kecikeci
1 of 3 tasks
v1.x
3
Failed to initialize NVML gpu stale
#3288 opened Apr 18, 2025 by pamdla
1 of 3 tasks
v1.x
2
ProTip! Adding no:label will show everything without a label.