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 42
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

81 Open 109 Closed
81 Open 109 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

Add eval benchmarks enhancement New feature or request
#347 opened May 6, 2025 by Blaizzy
@Blaizzy
4
Add AWQ/DWQ for Vision Models enhancement New feature or request
#346 opened May 6, 2025 by Blaizzy
@Blaizzy
Add Support for KV Cache Quantization
#345 opened May 6, 2025 by Blaizzy
Implement Persistent Prompt Cache to Reduce Time-to-First-Token in Chat Contexts enhancement New feature or request
#344 opened May 6, 2025 by Blaizzy
@Blaizzy
gemma-3-12b-pt-8bit is missing a chat processor
#338 opened May 4, 2025 by jrp2014
deepseek-vl2-8bit excessive diagnostics
#337 opened May 4, 2025 by jrp2014
Phi-3.5-vision-instruct end of output not properly detected
#336 opened May 4, 2025 by jrp2014
Output from generate is a tuple, rather than a string bug Something isn't working
#334 opened May 2, 2025 by jrp2014
7
Inaccurate Coordinate Outputs for MLX-Quantized UI-TARS-1.5 (4bit/6bit)
#330 opened Apr 28, 2025 by francedot
6
InternVL3 Multi-Image Support Broken
#328 opened Apr 23, 2025 by tmoroney
1
Revision Isn't Passed For Model Download
#324 opened Apr 22, 2025 by jbis9051
Adjusting sample_utils.py for top_k and min_p Parameters enhancement New feature or request
#317 opened Apr 20, 2025 by Blaizzy
Incorrect Output When Extracting Authors and Affiliations from Image using mlx_vlm.generate
#306 opened Apr 18, 2025 by Huy2002-IT
6
Cannot convert InternVL3-38B to MLX format
#305 opened Apr 18, 2025 by southkorea2013
2
Unrecognized image processor Qwen2_5_VLImageProcessor
#304 opened Apr 18, 2025 by hermeschen1116
Model type nemotron-nas not supported
#303 opened Apr 17, 2025 by doctorleach
Match the output of scipy.ndimage.zoom on multimodality's vision module resize_image()
#302 opened Apr 17, 2025 by Blaizzy
1
PaliGemma 2 mix segment multiple objects
#292 opened Apr 9, 2025 by JoeJoe1313
5
Does MLX-VLM support fine-tuning of vision tower layers?
#286 opened Apr 4, 2025 by sachinraja13
7
Issue with Finetuning Mistral (Mistral-Small-3.1-24B-Instruct-2503-4bit)
#284 opened Mar 30, 2025 by keshavpeswani
18
NAMO-R1 Model is Amazing! How to Convert it to MLX?
#277 opened Mar 26, 2025 by yourappleintelligence
Negative Prompt Support
#271 opened Mar 22, 2025 by yukiarimo
It seems that version v0.1.19 does not follow instructions and only describes images.
#259 opened Mar 19, 2025 by swlee60
3
Remove scipy dependency
#253 opened Mar 18, 2025 by r-bit-rry
4
OpenAI API
#247 opened Mar 15, 2025 by chigkim
5
ProTip! Type g i on any issue or pull request to go back to the issue listing page.