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

173 Open 1,284 Closed
173 Open 1,284 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

模型无法选择gpu，只有cpu选项 gpu
#2578 opened Nov 24, 2024 by wz96cj
1 of 3 tasks
v0.16
Dify调用xinfer中的rerank模型正常，ragflow调用xinfer中的rerank模型就OOM了 gpu
#2575 opened Nov 23, 2024 by cnrbi1
1 of 3 tasks
v0.16
xinference-client rerank has some bug
#2574 opened Nov 23, 2024 by swy0915
1 of 3 tasks
v0.16
4
xinference v1.0.0及以下版本需要升级transformer 4.45或以上，才可以正常启动qwen2-VL-instruct 模型 gpu
#2573 opened Nov 23, 2024 by cnrbi1
1 of 3 tasks
v0.16
1
Xinference use chattts BUG
#2570 opened Nov 21, 2024 by NieSf
1 of 3 tasks
v0.16
2
Add download progress management or optimizing logs feature
#2567 opened Nov 21, 2024 by redreamality v0.16
1
rerank模型不返回document信息
#2566 opened Nov 21, 2024 by mengxianglong123
1 of 3 tasks
v0.16
1
xinference v1.0.0无法正常启动qwen2-instruct gpu
#2564 opened Nov 21, 2024 by m199369309
1 of 3 tasks
v0.16
模型启动问题
#2563 opened Nov 21, 2024 by sdlssq
1 of 3 tasks
v0.16
1
update Xinference depends error gpu
#2561 opened Nov 20, 2024 by pingyuan2016
1 of 3 tasks
v0.16
requests.exceptions.JSONDecodeError: Expecting value: line 1 column 1 (char 0)
#2560 opened Nov 19, 2024 by ChengRuiLiang
1 of 3 tasks
v0.16
1
Got an Error while using Langchain Chatchat with internlm2.5. gpu
#2559 opened Nov 18, 2024 by frankSARU
1 of 3 tasks
v0.16
2
glm-4v模型只传文字报KeyError: 'images'，同时传文字和图片不报错
#2558 opened Nov 17, 2024 by JumpNew
1 of 3 tasks
v0.16
2
qwen2-instruct chat failed if set stop parameter
#2556 opened Nov 15, 2024 by liunux4odoo
1 of 3 tasks
v0.16
1
最新版本的xinference无法正常启动qwen2-vl-instruct模型 gpu
#2554 opened Nov 14, 2024 by majestichou
1 of 3 tasks
v0.16
9
为什么调用rerank模型后速度变慢了？ gpu stale
#2553 opened Nov 14, 2024 by fg2501
1 of 3 tasks
v0.16
2
vllm+cpu 后端（无 gpu 硬件）时，tensor_parallel_size 应该默认设置成 1 而不是 cuda_count(等于 0) gpu stale
#2552 opened Nov 14, 2024 by Diffizle
3 tasks
v0.16
2
在windows系统的conda中启动系统，提示错误信息。 gpu stale
#2550 opened Nov 14, 2024 by cns-cash
1 of 3 tasks
v0.16
1
加载 qwen2-vl-instruct 报错：cannot import name 'Qwen2VLForConditionalGeneration' from 'transformers'
#2549 opened Nov 14, 2024 by EthanKk
1 of 3 tasks
v0.16
1
Can we support paraformer? feature
#2548 opened Nov 13, 2024 by wy96f v0.16
1
H20显卡推理 glm9b-chat失败，版本0.16.3 gpu
#2544 opened Nov 12, 2024 by yangyu6
1 of 3 tasks
v0.16
3
寻求一个可以在一个GPU上部署多个小模型的方案 feature gpu
#2541 opened Nov 11, 2024 by RichardFans v0.16
2
0.16.3 版本docker镜像无法选择 sglang 作为推理引擎 gpu
#2537 opened Nov 11, 2024 by machgity
1 of 3 tasks
v0.16
3
vllm后端启动不支持异步 stale
#2529 opened Nov 7, 2024 by prettyprettyboy v0.16
7
部署glm-4v-9b模型后，模型可以加载但是无法进行对话，报[address=0.0.0.0:33271, pid=892267] ChatGLM4Tokenizer._pad() got an unexpected keyword argument 'padding_side' stale
#2523 opened Nov 5, 2024 by GengyuXu
1 of 3 tasks
v0.16
5
ProTip! Follow long discussions with comments:>50.