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

200 Open 1,113 Closed
200 Open 1,113 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

qwen2.5-instruct不支持tool calls
#2377 opened Sep 27, 2024 by yebanliuying
1 of 3 tasks
v0.15
FLUX.1-dev cpu and cuda:0 gpu
#2375 opened Sep 27, 2024 by sticktoFE
1 of 3 tasks
v0.15
1
启动Qwen2.5-7B-Instruct模型，能正常多卡启动，但推理失败 gpu
#2374 opened Sep 27, 2024 by joerunfu
1 of 3 tasks
v0.15
并发请求会导致current serve request count累加 gpu
#2373 opened Sep 26, 2024 by qdivan
1 of 3 tasks
v0.15
1
[Feature] Support for Llama 3.2 Multi-modal and Lightweight Models feature
#2372 opened Sep 26, 2024 by vikrantrathore v0.15
2
How can I use Multi-vector retrieval embedding throught xinference client? feature
#2371 opened Sep 26, 2024 by HuuHuy227 v0.15
1
internvl2无法下载 gpu
#2369 opened Sep 25, 2024 by SDAIer
1 of 3 tasks
v0.15
Qwen2.5 7b显存占用过大
#2368 opened Sep 25, 2024 by mengxianglong123 v0.15
4
请问是否考虑支持嵌入模型：MiniCPM-Embedding feature
#2365 opened Sep 25, 2024 by CharmingDaiDai v0.15
Xinference部署qwen2-vl为啥生成速度那么慢啊，感觉不正常
#2364 opened Sep 25, 2024 by kandada
1 of 3 tasks
v0.15
2
embedding模型增加对于gguf格式的支持 feature gpu
#2363 opened Sep 25, 2024 by ConleyKong v0.15
xinference tool calls does not support stream mode feature
#2362 opened Sep 25, 2024 by Dofine-dufei v0.15
Can not deploy qwen2-vl gpu
#2361 opened Sep 24, 2024 by wangzuohao
1 of 3 tasks
v0.15
3
vllm方式多卡加载模型卡住，GPU占用率100% gpu
#2360 opened Sep 24, 2024 by Dax-Zhang-pxy
1 of 3 tasks
v0.15
输出的时候，应该回答一半就会停止，给人的感觉就是没有没有回答完整。是上下文长度的原因吗
#2359 opened Sep 24, 2024 by Joker-sad
3 tasks
v0.15
1
0.15.2版本xinference启动本地模型报错Model not found gpu
#2358 opened Sep 24, 2024 by wujingbo-web
1 of 3 tasks
v0.15
1
xinference vllm inference qwen2.5 128k 返回空
#2357 opened Sep 24, 2024 by JasonFlyBeauty
1 of 3 tasks
v0.15
运行的GPU有资源，却提示别的GPU资源不够 gpu
#2356 opened Sep 24, 2024 by SDAIer
1 of 3 tasks
v0.15
XF提示exceed limit gpu
#2355 opened Sep 24, 2024 by SDAIer
1 of 3 tasks
v0.15
8
install FAILED: vendor/llama.cpp/examples/llava/llama-minicpmv-cli
#2354 opened Sep 23, 2024 by trackcan
1 of 3 tasks
v0.15
1
SGlang部署qwen2.5失败Exception: Capture cuda graph failed: BatchPrefillWithPagedKVCache failed with error code no kernel image is available for execution on the device gpu
#2351 opened Sep 23, 2024 by dingidng
1 of 3 tasks
v0.15
7
启动qwen2.5 14B vllm int8 版本ValueError: [address=0.0.0.0:37961, pid=352437] Marlin does not support weight_bits = uint8b128. Only types = [] are supported (for group_size = 128, min_capability = 70, zp = False) gpu
#2350 opened Sep 23, 2024 by dingidng
1 of 3 tasks
v0.15
1
建议增加对嵌入模型 jina-embeddings-v3 的支持 feature
#2349 opened Sep 23, 2024 by dongkuang v0.15
@amumu96
1
client.launch_model api 建议增加 按最近默认配置启动的功能类似 feature
#2348 opened Sep 23, 2024 by ZanePoe v0.15
FEAT: Qwen2.5 support function calling feature
#2347 opened Sep 23, 2024 by a2382625920 v0.15
7
ProTip! Add no:assignee to see everything that’s not assigned.