Issues
- 13
Make mlx-vlm examples in swift
#132 opened by davidkoski - 2
- 0
[Bug] Llama 3 DynamicNTK RoPE is incorrect
#152 opened by awni - 3
- 3
Huggingface mlx-community/Phi-3-mini-128k-instruct-4bit model cannot be loaded
#92 opened by neilmehta24 - 0
- 3
Xcode Cloud
#143 opened by zach-withcoherence - 1
Has anyone successfully run Whisper in Swift?
#146 opened by AmanKishore - 1
Xcode refuses to build or do anything after adding https://github.com/ml-explore/mlx-swift-examples/ as dependency
#145 opened by coratype - 3
- 1
- 0
OLMoE @ mlx-swift
#141 opened by aPaleBlueDot - 1
Crash on launch of the application
#139 opened by venkadesh-p - 2
How to remove model from memory after loading
#138 opened by resolvepalapp - 6
Is there a good way to load the Flux.1 T5 tokenizer?
#136 opened by mzbac - 5
LLMEval doesn’t work offline
#113 opened by 3Samourai - 0
use dynamic bundle identifier in examples
#128 opened by davidkoski - 17
Crash on `concatenate` after latest update
#114 opened by DePasqualeOrg - 3
Update to swift-transformers
#117 opened by johnmai-dev - 6
- 0
- 0
gpt-neox @ mlx-swift
#94 opened by aPaleBlueDot - 6
Things Crash on MacOS Beta
#96 opened by amirsafaei - 2
Gigabyte top ai utility
#105 opened by Isaina - 3
Unable to allocate memory
#84 opened by aidinrs - 5
Avoid exceeding maximum allowed buffer size
#106 opened by DePasqualeOrg - 5
Crash when start
#101 opened by xlisp - 8
MLX/Transforms+Eval.swift:166: Fatal error: Unable to extract MLXArray from idle
#102 opened by aPaleBlueDot - 5
Prepare for strict concurrency in Swift 6
#82 opened by DePasqualeOrg - 2
- 9
Gemma 2 output includes `<end_of_turn>`
#89 opened by DePasqualeOrg - 2
- 3
[Enhancement] Run as background app
#81 opened by awni - 6
Publish releases with version numbers
#79 opened by DePasqualeOrg - 1
Prompt template for OpenELM instruct models
#73 opened by DePasqualeOrg - 19
- 2
- 5
Phi-3 mini stop token not recognized
#74 opened by DePasqualeOrg - 4
- 3
- 2
Download progress is not accurate
#77 opened by DePasqualeOrg - 5
LLMEval: "Cycle inside LLMEval; building could produce unreliable results" build error
#64 opened by ddiddi - 7
- 2
GPU Memory/Cache Limit
#66 opened by r4ghu - 2
- 12
When to stop in the LLMEval?
#56 opened by MatthewWaller - 3
OpenELM example?
#55 opened by MatthewWaller - 6
Package.resolved
#57 opened by ajayjapan - 2
llm-tool CoreDevice error (The provided item to be installed is not of a type that CoreDevice recognizes)
#61 opened by h21k - 5
Phi-3 on iOS,
#59 opened by fromparis