Skip to content

Issues: QwenLM/Qwen2-VL

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

256 Open 141 Closed
256 Open 141 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

Floating point exception
#554 opened Nov 21, 2024 by sally153
vllm 0.6.4 还是报错
#553 opened Nov 21, 2024 by dhhcj1
多图推测无法成功
#552 opened Nov 21, 2024 by csc365kl
Qwen2-VL-72B vLLM Response Issue with Larger Images: Short and Incomplete Outputs
#551 opened Nov 20, 2024 by KaranBhuva22
Misspelling "Native" Dynamic Resolution
#550 opened Nov 20, 2024 by SiyangJ
vllm部署之后，客户端后者后端应用如何访问API
#548 opened Nov 20, 2024 by ybshaw
不管使用A6000*4还是A800*4推理2B, 7B还是72B模型，选择device_map=auto都会出现各种奇怪的报错，只有device_map="cuda:x"单卡才能正常使用
#546 opened Nov 19, 2024 by luosting
用vllm部署Qwen2-VL-7B-Instruct模型，单次请求输入2张图片生成内容不完整，输入单张图片生成内容是完整的
#545 opened Nov 19, 2024 by xj260098061
Qwen2-VL 最大输出tokens数 最多只能是1024吗
#544 opened Nov 19, 2024 by Mhw-git
将Qwen2-VL模型转化为ONNX格式并用C++推理
#543 opened Nov 18, 2024 by shengqihailuo1
Qwen-VL-7B model +vllm assert len(indices) == len(inputs) AssertionError
#542 opened Nov 18, 2024 by sssunXw
Qwen-VL-7B model memory issue
#541 opened Nov 18, 2024 by Dineshkumar-Anandan-ZS0367
1
qwen2Vl+vllm框架如何添加视频内容
#540 opened Nov 18, 2024 by zhangzhiyuan303
qwen2Vl+vllm框架如何添加视频内容
#539 opened Nov 18, 2024 by zhangzhiyuan303
请问qwen2-vl上有做过大小分辨率相关的实验吗，能否提升模型精度
#538 opened Nov 18, 2024 by qqqq-0
Confusion about the effect of special tokens on model fine-tuning.
#537 opened Nov 18, 2024 by Davidwhw
视觉定位refcoco评测和官方结果稍有误差，请问官方的prompt是什么
#536 opened Nov 16, 2024 by Michael4933
1
使用vllm和transformer部署Qwen2vl，同一张图片输出结果不一致
#535 opened Nov 15, 2024 by Apricot1225
给的requirements_web_demo.txt文件有问题吗
#534 opened Nov 14, 2024 by bisque-qwe
1
what is the text ability of Qwen2-VL?
#533 opened Nov 13, 2024 by fake-warrior8
is there a way to reduce vRAM usage & speed up vLLM inference for AWQ?
#532 opened Nov 12, 2024 by mehamednews
1
A small mistake in the GPTQ section of the README.
#531 opened Nov 12, 2024 by MTDoven
Prebuild flash attention wheels!
#530 opened Nov 12, 2024 by kunibald413
通义千问2-VL-2B-Instruct-GPTQ-Int4不支持多轮图片识别
#529 opened Nov 12, 2024 by HaoWang81
1
qwen2-vl, vllm 推理错误
#528 opened Nov 12, 2024 by peiliu0408
ProTip! What’s not been updated in a month: updated:<2024-10-23.