Blaizzy/mlx-vlm

Issues

• Batch Processing Feature

  #40 opened 7 months ago by Blaizzy
  6

• [Feature Request] Supports fine-tuning

  #49 opened 2 months ago by madroidmaq
  5

• How to continue a conversation with more images?

  #68 opened 3 months ago by simonw
  8

• Chat UI error when prompt is longer than one character

  #108 opened 2 months ago by faev999
  0

• gradio chat exception

  #103 opened 2 months ago by faev999
  3

• Some picture captioning results with various models, for reference

  #107 opened 2 months ago by jrp2014
  0

• LLaVa-NeXT needs tweaking for v4.47

  #106 opened 2 months ago by jrp2014
  0

• Models to port to MLX-VLM

  #39 opened 7 months ago by Blaizzy
  20

• Is it possible to call these vision llm's in Swift ?

  #104 opened 2 months ago by kunal732
  0

• Error: Invalid high padding size

  #102 opened 2 months ago by pwichmann
  7

• Pixtral text/image prompt order

  #98 opened 2 months ago by ndurner
  0

• Support for SDXL 3.5

  #101 opened 2 months ago by bhupesh-sf
  0

• Very High Memory Usage for Llama-3.2-11B-Vision-Instruct-4bit

  #100 opened 2 months ago by chigkim
  1

• Qwen2-VL-7B-Instruct-4bit allocation crashes on larger dimension images

  #79 opened 2 months ago by mattjcly
  17

• Support for Null Image input

  #94 opened 2 months ago by dtoconnor
  1

• Which specific models work with this framework?

  #80 opened 3 months ago by jrp2014
  25

• Expanding inputs for image tokens in LLaVa-NeXT should be done in processing

  #93 opened 2 months ago by jrp2014
  0

• [Feature Request] Add support for h2ovl

  #92 opened 3 months ago by a-ghorbani
  0

• LLaMA 3.2 11B Vision Support

  #60 opened 3 months ago by yukiarimo
  8

• Nan loss when training Llama-3.2-vision

  #84 opened 3 months ago by Blaizzy
  11

• Video Input

  #88 opened 3 months ago by chigkim
  3

• Qwen2-VL-72B-Instruct-4bit?

  #86 opened 3 months ago by chigkim
  2

• Pixtral Multi-Image Bug

  #87 opened 3 months ago by mattjcly
  1

• Still having issue with mlx-community/pixtral-12b-8bit model execution

  #85 opened 3 months ago by gitrodg1
  3

• Getting 'NameError: name 'config' is not defined' when running example scripts

  #81 opened 3 months ago by mark-lord
  2

• Can't get pixtral-12b to work

  #69 opened 3 months ago by beaugunderson
  6

• Error running mlx-community/pixtral-12b-4bit

  #73 opened 3 months ago by jpschreiter
  1

• Qwen2-VL: Model Test Structure Improvements

  #76 opened 3 months ago by benzimring
  2

• Qwen2-VL `lm_head` Weight Sanitization Prefixes

  #61 opened 3 months ago by benzimring
  7

• Error running mlx-community/Qwen2-VL-7B-4bit

  #71 opened 3 months ago by jpschreiter
  8

• Support for Video with Qwen2-VL

  #75 opened 3 months ago by tmoroney
  4

• load() pulling tokenizer instead of processor for deepseek

  #58 opened 3 months ago by michaellee1
  2

• Cannot install mlx-vlm because these package versions have conflicting dependencies.

  #74 opened 3 months ago
  2

• Trust remote code mlx-community/Phi-3.5-vision-instruct-4bit

  #72 opened 3 months ago by jpschreiter
  3

• Please add support for Molmo

  #70 opened 3 months ago by xSNYPSx
  1

• Addition of Qwen2-VL support broke compatibility with previous models

  #65 opened 3 months ago by benzimring
  0

• Errors when running example script

  #66 opened 3 months ago by DePasqualeOrg
  4

• unable to run paligemma

  #38 opened 5 months ago by nischalj10
  8

• Phi-3.5-vision-instruct-bf16 fails

  #56 opened 4 months ago by jrp2014
  5

• LLVM 1.6 is quite good, but could be better

  #52 opened 5 months ago by jrp2014
  2

• Chat template error with MLX Community LLava models (moved from FastMLX)

  #51 opened 5 months ago by stewartugelow
  16

• Idefics2: Inconsistent converted model outputs and special token leakage

  #32 opened 5 months ago by civvic
  8

• LLava documentation?

  #47 opened 6 months ago by jrp2014
  16

• Batch inference support (self-assigning)

  #48 opened 6 months ago by willccbb
  2

• Can't run deepseek-vl with script on M2

  #46 opened 6 months ago by WayneCui
  6

• Feature Request: Support for `phi-3-vision-128k-instruct`

  #28 opened 6 months ago by JosefAlbers
  19

• ChatUI improvements

  #45 opened 6 months ago by Blaizzy
  0

• Llava v1.6 support

  #42 opened 6 months ago by jrp2014
  2

• Error running inference script in readme using paligemma-3b-mix-448-8bit

  #33 opened 7 months ago by mobile-appz
  3

• Inconsistent OCR results with Idefics2 model in mlx_vlm compared to other environments

  #30 opened 7 months ago by civvic
  7