Skip to content

Issues: deepseek-ai/DeepSeek-VL2

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

94 Open 19 Closed
94 Open 19 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

示例代码是不是写错了“outputs = vl_gpt.language_model.generate(”
#135 opened May 21, 2025 by CanIChangeName
怎么使用System Prompt？System Prompt似乎没有意义。
#134 opened May 1, 2025 by yuan2001425
deepseek-vl2可以使用纯cpu+内存的方式进行部署么
#133 opened Apr 25, 2025 by wangpf09
Running Inference on Multiple GPU
#132 opened Apr 24, 2025 by Mukil07
1
Incremental Prefilling error
#131 opened Apr 12, 2025 by UchihaIchigo
pure-text data format
#130 opened Apr 9, 2025 by hongjian
1
Significant Discrepancies Between Batch Inference and Single Inference in DeepSeekVL2
#129 opened Apr 8, 2025 by j1ajunzhu
I use swift fine-tuning, infer test set reasoning on the following problems, ask for your help!!
#128 opened Apr 7, 2025 by Jackson-cj
1
Simple Inference Example with Multiple Images 输出问题
#127 opened Apr 6, 2025 by winter-JX
deepseek-vl2 Abnormal output
#126 opened Apr 2, 2025 by orzgugu
1
ValueError: The checkpoint you are trying to load has model type deepseek_vl_v2 but Transformers does not recognize this architecture. This could be because of an issue with the checkpoint, or because your version of Transformers is out of date.
#125 opened Apr 2, 2025 by xjtu-hxy
Is Multi-head Latent Attention used in DeepSeek-VL2 tiny?
#124 opened Mar 31, 2025 by niktheod
When evaluating the RefCOCO dataset using the example code, the accuracy is very low.
#123 opened Mar 30, 2025 by haoxiangzhao12138
4
Why we have local views even in cropping is False?
#122 opened Mar 27, 2025 by Dinngger
bbox+ocr
#121 opened Mar 27, 2025 by gedebachichi
When testing with web_demo.by, there was no problem with asking text, but when uploading images and asking questions again, the program crashed directly.
#120 opened Mar 26, 2025 by rxzhuang
bf16 is only supported on A100+ GPUs，how can i use torch.float16
#119 opened Mar 20, 2025 by Nick280375880
5
Request for Official MMMU-val Evalution Script
#117 opened Mar 18, 2025 by willburwwb
The deepseek-vl2-tiny gets the wrong output
#116 opened Mar 15, 2025 by MRYUjg
"Innovative Proposal to Revolutionize User Engagement for Deepseek"
#115 opened Mar 15, 2025 by mrsyllas
Multi round dialogue
#114 opened Mar 14, 2025 by OuHR
load deepseek-vl2模型设定device_map="balanced"时，inference报错
#113 opened Mar 11, 2025 by Chord-Chen-30
1
vllm输出结果质量低
#111 opened Mar 7, 2025 by chenyzh28
1
兼容新版transformers
#110 opened Mar 7, 2025 by Alane-Henry
dispatch_model cannot put some parameter to cuda
#109 opened Mar 4, 2025 by erikchwang
ProTip! Type g p on any issue or pull request to go back to the pull request listing page.