Skip to content

Issues: Blaizzy/mlx-vlm

Batch Processing Feature
#40 opened Jun 11, 2024 by Blaizzy
Open 6
ChatUI improvements
#45 opened Jun 23, 2024 by Blaizzy
Open
Models to port to MLX-VLM
#39 opened Jun 11, 2024 by Blaizzy
Open 41
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

59 Open 82 Closed
59 Open 82 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

Gemma 3 Chat UI Broken?
#243 opened Mar 12, 2025 by vessenes
1
Gemma 3 models do not see the image when the prompt is too long
#242 opened Mar 12, 2025 by asmeurer
Add FastAPI server enhancement New feature or request good first issue Good for newcomers
#241 opened Mar 12, 2025 by Blaizzy
Any speed reference compare with candle or llama.cpp with Qwen2.5 VL 4B?
#240 opened Mar 12, 2025 by MonolithFoundation
Gemma3 - TypeError: PreTrainedTokenizerFast._batch_encode_plus() got an unexpected keyword argument 'images'
#238 opened Mar 12, 2025 by alexl4321
10
Add support for Gemma 3?
#237 opened Mar 12, 2025 by alexgusevski
7
[Question] Using Video api with list of image frame
#233 opened Mar 11, 2025 by remichu-ai
Generating text using Qwen2.5 Vision model
#231 opened Mar 7, 2025 by yukiarimo
1
Ensure backwards compatibility with transformers good first issue Good for newcomers
#230 opened Mar 6, 2025 by Blaizzy
Support Phi-4-multimodal
#225 opened Mar 5, 2025 by kinfey
Computer use is not working
#223 opened Mar 3, 2025 by southkorea2013
1
Running Siglip/Siglip2 on MLX?
#219 opened Feb 27, 2025 by maxlund
4
Negative padding bug Something isn't working
#214 opened Feb 23, 2025 by pavelgur
2
KeyError: 'image_token_index' bug Something isn't working
#213 opened Feb 23, 2025 by pavelgur
@Blaizzy
2
Add support for Ovis 2 ? enhancement New feature or request
#212 opened Feb 22, 2025 by alexgusevski
4
Models should not need to be re-loaded between back-to-back prompts bug Something isn't working
#210 opened Feb 21, 2025 by neilmehta24
2
Unrecognized image processor in mlx-community/Qwen2.5-VL-7B-Instruct-4bit
#209 opened Feb 21, 2025 by leoho0722
6
When will Janus-Pro be supported?
#204 opened Feb 18, 2025 by fackweb
temp or temperature?
#203 opened Feb 7, 2025 by asmeurer
4
Add AutoModel support
#193 opened Jan 30, 2025 by not-lain
3
Error in FineTuning deepseek-vl-7b-chat-8bit bug Something isn't working
#187 opened Jan 27, 2025 by sachinraja13
@Blaizzy
2
Chat UI from readme fails
#186 opened Jan 22, 2025 by andimarafioti
2
mlx-community/deepseek-vl2-8bit config excessive, pad_token / image_token missing? Verbose param affects results??
#183 opened Jan 17, 2025 by jrp2014
Fine Tuning Llava-Next
#181 opened Jan 13, 2025 by sachinraja13
lava-v1.6: unsupported operand type(s) for //: 'int' and 'NoneType'
#178 opened Jan 10, 2025 by jrp2014
15
ProTip! Type g p on any issue or pull request to go back to the pull request listing page.