Owner

ml-explore

9 indexed repositories · View on GitHub

mlx
MLX: An array framework for Apple silicon

C++ · 28488 stars
mlx-examples
Examples in the MLX framework

Python · 8957 stars
mlx-lm
Run LLMs with MLX

Python · 7073 stars
mlx-swift-examples
Examples using MLX Swift

Swift · 2666 stars
mlx-swift
Swift API for MLX

C++ · 2037 stars
mlx-swift-lm
LLMs and VLMs with MLX Swift

Swift · 810 stars
mlx-data
Efficient framework-agnostic data loading

C++ · 483 stars
mlx-c
C API for MLX

C++ · 243 stars
mlx-onnx
MLX support for the Open Neural Network Exchange (ONNX)

72 stars

Beginner friendly Everything

Open All

`mlx` no longer builds from source with Xcode 27 (macOS 27.0 SDK) Open

Difficulty 2/5 1-3 hours Newbie friendliness 88/100

ml-explore/mlx#4533 · Opened Sep 18, 2026
mx.compile inlines float scalar constants with 7 significant digits, so compiled results differ from eager by 1 ulp Open

Difficulty 2/5 1-3 hours Newbie friendliness 85/100

ml-explore/mlx#4503 · 1 comment · Opened Sep 14, 2026
`phimoe.py` subscripts `rope_scaling` unconditionally, so `Phi-mini-MoE-instruct` dies with a bare `TypeError` Open

Difficulty 2/5 1-3 hours Newbie friendliness 76/100

ml-explore/mlx-lm#1884 · Opened Sep 13, 2026
gated_delta: vectorized Metal kernel reads dt_bias per-head; callers (kimi_linear) pass per-element [H, head_dim] — GPU/CPU gate mismatch Open

Difficulty 2/5 1-3 hours Newbie friendliness 82/100

ml-explore/mlx-lm#1792 · Opened Aug 27, 2026
mlx_median with no axis (axes=NULL, axes_num=0) fails: [flatten] start_axis must be less than or equal to end_axis Open

Difficulty 2/5 1-3 hours Newbie friendliness 84/100

ml-explore/mlx-c#128 · Opened Aug 23, 2026
Gemma 4 VLM path builds k_proj/v_proj for KV-shared layers, so E2B/E4B checkpoints fail to load Open

Difficulty 2/5 1-3 hours Newbie friendliness 88/100

ml-explore/mlx-swift-lm#558 · 3 comments · Opened Aug 20, 2026
[whisper] `mlx_whisper` CLI overwrites output file when multiple audio inputs are provided Open

Difficulty 2/5 1-3 hours Newbie friendliness 85/100

ml-explore/mlx-examples#1441 · Opened Aug 18, 2026
vmap of scatter silently returns wrong values when the vmap axis is >= 2 Open

bug low priority

Difficulty 2/5 1-3 hours Newbie friendliness 72/100

ml-explore/mlx#4321 · 1 comment · Opened Aug 17, 2026
Code in the first example for Python SDK do not pass type check on load()'s returned values Open

Difficulty 2/5 1-3 hours Newbie friendliness 68/100

ml-explore/mlx-lm#1732 · Opened Aug 14, 2026
load() pays an avoidable Hub round-trip per call even when the model is fully cached Open

Difficulty 2/5 1-3 hours Newbie friendliness 78/100

ml-explore/mlx-lm#1649 · Opened Aug 3, 2026
Stable Diffusion: Transformer2D's GroupNorm uses MLX's default eps (1e-5) where diffusers uses 1e-6 Open

Difficulty 1/5 Under an hour Newbie friendliness 84/100

ml-explore/mlx-examples#1434 · Opened Jul 31, 2026
Package.swift exclude list breaks when the mlx pin moves past v0.31.2 (jaccl restructured) Open

Difficulty 2/5 1-3 hours Newbie friendliness 68/100

ml-explore/mlx-swift#446 · 2 comments · Opened Jul 30, 2026
/v1/models commits 200 before scan_cache_dir(), hiding CacheNotFound Open

Difficulty 2/5 1-3 hours Newbie friendliness 72/100

ml-explore/mlx-lm#1636 · 1 comment · Opened Jul 29, 2026
Importing mlx_lm lowers RLIMIT_NOFILE and irreversibly caps the hard limit Open

Difficulty 2/5 1-3 hours Newbie friendliness 78/100

ml-explore/mlx-lm#1589 · Opened Jul 20, 2026
`mlx_lm.server` pins a CPU core at ~100% while idle (generation worker busy-polls the request queue with `get_nowait()`) Open

Difficulty 2/5 1-3 hours Newbie friendliness 78/100

ml-explore/mlx-lm#1500 · 6 comments · Opened Jul 8, 2026
Please bump the vendored mlx-core so the batched single-token RoPE fix (ml-explore/mlx#3498) reaches mlx-swift Open

Difficulty 2/5 1-3 hours Newbie friendliness 88/100

ml-explore/mlx-swift#441 · 5 comments · Opened Jul 8, 2026
[BUG] mx.expm1 is wrong for complex inputs (discards imaginary part) Open

bug

Difficulty 2/5 1-3 hours Newbie friendliness 72/100

ml-explore/mlx#3759 · Opened Jun 24, 2026
server: add --lazy CLI flag for deferred model loading Open

Difficulty 2/5 1-3 hours Newbie friendliness 78/100

ml-explore/mlx-lm#1428 · Opened Jun 24, 2026
whisper: align no_speech_threshold fallback condition with openai/whisper Open

Difficulty 2/5 1-3 hours Newbie friendliness 76/100

ml-explore/mlx-examples#1427 · Opened Jun 18, 2026
mlx_lm.server assigns 36-char UUID tool-call ids, which Mistral v3 templates reject (length-9 constraint) Open

Difficulty 2/5 1-3 hours Newbie friendliness 68/100

ml-explore/mlx-lm#1375 · Opened Jun 8, 2026
whisper/convert.py outputs `model.safetensors` but `mlx_whisper.load_models` expects `weights.safetensors` Open

Difficulty 2/5 1-3 hours Newbie friendliness 68/100

ml-explore/mlx-examples#1421 · 1 comment · Opened May 1, 2026
[whisper] `KeyError: 'words'` on transcription (with `--task translate`) Open

Difficulty 2/5 1-3 hours Newbie friendliness 78/100

ml-explore/mlx-examples#1418 · Opened Apr 24, 2026
Gemma4 (MLXLLM): K-eq-V attention path double-transposes V, causes broadcast_shapes crash Open

Difficulty 2/5 1-3 hours Newbie friendliness 68/100

ml-explore/mlx-swift-lm#231 · 1 comment · Opened Apr 22, 2026
TokenRing.loadPrompt crash: prompt.dim(0) returns batch dim for 2D tensors Open

Difficulty 2/5 1-3 hours Newbie friendliness 72/100

ml-explore/mlx-swift-lm#220 · 1 comment · Opened Apr 17, 2026

ml-explore

Get new issues in your inbox