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
RFC: Branchable KV cache with shared-prefix / copy-on-write semantics Open

Difficulty 5/5 Over a week Newbie friendliness 25/100

ml-explore/mlx-swift-lm#629 · Opened Sep 18, 2026
Missing general Knowledge Distillation paradigm Open

Difficulty 5/5 Over a week Newbie friendliness 25/100

ml-explore/mlx-lm#1900 · Opened Sep 17, 2026
[BUG] Metal `col_reduce_longcolumn` produces wrong results for negative-stride views Open

Difficulty 3/5 1-2 days Newbie friendliness 25/100

ml-explore/mlx#4528 · Opened Sep 17, 2026
ParallelFileReader: uncatchable fatal error when pread lands at EOF Open

Difficulty 4/5 3-5 days Newbie friendliness 58/100

ml-explore/mlx#4526 · Opened Sep 17, 2026
macOS 26 wheel is built for 26.2 but tagged macosx_26_0 — pip installs it on 26.0/26.1, where NAX is enabled on M5-class GPUs Open

Difficulty 4/5 3-5 days Newbie friendliness 55/100

ml-explore/mlx#4525 · Opened Sep 17, 2026
Read Gemma tool-call arguments with a dialect parser instead of rewriting them into JSON Open

Difficulty 5/5 Over a week Newbie friendliness 25/100

ml-explore/mlx-swift-lm#628 · Opened Sep 17, 2026
Metal command-buffer limits (50 ops / 50 MB) cost 5–8% decode throughput on launch-heavy models (M3 Ultra measurements) Open

Difficulty 4/5 3-5 days Newbie friendliness 45/100

ml-explore/mlx#4521 · Opened Sep 16, 2026
Can we add support for deepseek v4.1? Open

Difficulty 5/5 Over a week Newbie friendliness 25/100

ml-explore/mlx-lm#1894 · 1 reaction · Opened Sep 16, 2026
[BUG] ToolCallProcessor rescans the whole collected call for its end tag on every chunk Open

Difficulty 3/5 1-2 days Newbie friendliness 64/100

ml-explore/mlx-swift-lm#624 · Opened Sep 15, 2026
mlx_lm.server: option to restrict which models a request may load (allow-list) Open

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

ml-explore/mlx-lm#1892 · Opened Sep 15, 2026
RuntimeError: There is no Stream(gpu, 3) in current thread at KVCache __del__ teardown Open

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

ml-explore/mlx-lm#1888 · Opened Sep 14, 2026
[BUG] asArray with zero dimension array crashes Open

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

ml-explore/mlx-swift#480 · 1 comment · Opened Sep 14, 2026
[Performance] gather_qmm at M=1 streams 4-bit expert weights at ~half the bandwidth of M=4 (MoE decode) Open

Difficulty 5/5 Over a week Newbie friendliness 45/100

ml-explore/mlx#4509 · Opened Sep 14, 2026
[BUG] threads and streams issues Open

Difficulty 5/5 Over a week Newbie friendliness 30/100

ml-explore/mlx#4506 · 1 comment · Opened Sep 14, 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
[BUG] `argsort` diverges between cpu and gpu on complexes with NaN Open

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

ml-explore/mlx#4502 · Opened Sep 14, 2026
quantized_matmul is slower than dense bf16 when the output dimension is not a multiple of 8, and ~7x slower below 8 Open

Difficulty 4/5 3-5 days Newbie friendliness 42/100

ml-explore/mlx#4498 · Opened Sep 13, 2026
MiniCPM5-1B-MLX tool calling not supported by mlx_lm.server Open

Difficulty 4/5 3-5 days Newbie friendliness 55/100

ml-explore/mlx-lm#1885 · 2 reactions · Opened Sep 13, 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
`Lfm2MoeSparseMoeBlock` routing diverges from HF: softmax instead of sigmoid, `expert_bias` in the weights, and `routed_scaling_factor` dropped Open

Difficulty 3/5 1-2 days Newbie friendliness 74/100

ml-explore/mlx-lm#1883 · Opened Sep 13, 2026
RotatingKVCache cannot trim, so a serving layer cannot rewind a divergent prefix Open

Difficulty 5/5 Over a week Newbie friendliness 42/100

ml-explore/mlx-swift-lm#618 · 3 comments · Opened Sep 11, 2026
Release soon? Open

Difficulty 4/5 3-5 days Newbie friendliness 35/100

ml-explore/mlx-swift-lm#617 · 13 comments · 2 reactions · Opened Sep 10, 2026
Support for k2_horizon Request. Open

Difficulty 4/5 3-5 days Newbie friendliness 45/100

ml-explore/mlx-lm#1876 · Opened Sep 10, 2026
Missing support for Orion model architecture Open

Difficulty 4/5 3-5 days Newbie friendliness 35/100

ml-explore/mlx-lm#1874 · 1 comment · Opened Sep 10, 2026
ArraysCache metadata graph grows during sustained Qwen3.8-27B batch decoding Open

Difficulty 4/5 3-5 days Newbie friendliness 25/100

ml-explore/mlx-lm#1871 · Opened Sep 10, 2026
[BUG] VJP should be Sendable Open

Difficulty 4/5 3-5 days Newbie friendliness 48/100

ml-explore/mlx-swift#475 · 3 comments · Opened Sep 9, 2026
[BUG] JACCL segfaults in mx.distributed.init(backend="jaccl") on 2-node Mac-Mac with RDMA devices present Open

Difficulty 4/5 3-5 days Newbie friendliness 45/100

ml-explore/mlx#4485 · 1 comment · Opened Sep 9, 2026
mx.dequantize returns garbage on CPU past 2^31 unpacked bits (int size in cpu/binary.h) Open

bug low priority

Difficulty 4/5 3-5 days Newbie friendliness 54/100

ml-explore/mlx#4479 · 4 comments · Opened Sep 8, 2026
mx.distributed ring backend: gradient-shaped CPU-stream all_sum deadlocks probabilistically (~3-4%/call) across a training loop; GPU-stream variant crashes deterministically at ~5s Open

bug distributed

Difficulty 5/5 Over a week Newbie friendliness 35/100

ml-explore/mlx#4475 · 1 comment · Opened Sep 8, 2026
segment_anything: fuse attention with mx.fast.scaled_dot_product_attention Open

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

ml-explore/mlx-examples#1451 · Opened Sep 7, 2026
Community project: Depth-Anything-V2 running via a from-scratch PyTorch-API shim (torch-mlx) Open

Difficulty 4/5 3-5 days Newbie friendliness 25/100

ml-explore/mlx-examples#1449 · Opened Sep 7, 2026
Tagged release carrying mlx#3810 (NAX split-K GEMM dtype fix) without the rest of the v0.32.2 vendor bump? Open

Difficulty 5/5 Over a week Newbie friendliness 35/100

ml-explore/mlx-swift#470 · 3 comments · Opened Sep 6, 2026
Paged KV storage and external cache integration Open

Difficulty 5/5 Over a week Newbie friendliness 35/100

ml-explore/mlx-lm#1849 · 1 comment · Opened Sep 5, 2026
`ArraysCache.advance()` still leaks one Metal buffer per SSM layer per token through `BatchGenerator` after #1632 — long completions crash at ~499000/(#SSM−1) tokens on main Open

Difficulty 4/5 3-5 days Newbie friendliness 68/100

ml-explore/mlx-lm#1845 · Opened Sep 4, 2026
Einsum selects unsupported matmul for integer contractions Open

documentation low priority

Difficulty 4/5 3-5 days Newbie friendliness 68/100

ml-explore/mlx#4463 · 5 comments · Opened Sep 4, 2026
DFlash2 speculative decoding for Qwen3.8-27B Open

Difficulty 5/5 Over a week Newbie friendliness 30/100

ml-explore/mlx-swift-lm#606 · 1 comment · 1 reaction · Opened Sep 4, 2026
Scan primitive lacks output_shapes for shapeless compile Open

enhancement low priority

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

ml-explore/mlx#4460 · Opened Sep 4, 2026
RFC: Streaming conversion - quantize checkpoints larger than local disk in `mlx_lm.convert` Open

Difficulty 5/5 Over a week Newbie friendliness 35/100

ml-explore/mlx-lm#1842 · Opened Sep 4, 2026
mlx_lm.server deadlocks in mlx::core::eval_impl (condition_variable::wait) when the prompt cache is full under concurrent load — no Python exception Open

Difficulty 5/5 Over a week Newbie friendliness 28/100

ml-explore/mlx-lm#1834 · 1 reaction · Opened Sep 3, 2026
[BUG] Inconsistent behaviour of the floot_divide integer arrays truncates towards 0 Open

bug low priority

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

ml-explore/mlx#4450 · 5 comments · Opened Sep 2, 2026
[BUG] Silently wrong grad and vmap for a strided slice that selects exactly one element Open

bug low priority

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

ml-explore/mlx#4444 · Opened Sep 1, 2026
Metal: distributed collectives run on the CPU stream, and with the default fence each crossing costs ~180 µs (MLX_METAL_FAST_SYNCH: ~4 µs) Open

distributed performance

Difficulty 5/5 Over a week Newbie friendliness 35/100

ml-explore/mlx#4438 · 2 comments · Opened Aug 31, 2026
`nn.Upsample(mode="linear")` is 2-4x slower than a matmul-based bilinear resize when upsampling Open

performance

Difficulty 4/5 3-5 days Newbie friendliness 48/100

ml-explore/mlx#4435 · 4 comments · Opened Aug 30, 2026
Long-running mlx_lm.server: memory grows unboundedly past prompt-cache cap on hybrid-attention models (Qwen3.8-27B 4-bit) Open

Difficulty 4/5 3-5 days Newbie friendliness 35/100

ml-explore/mlx-lm#1807 · Opened Aug 30, 2026
[ENH]: Using `IndexError` instead of `ValueError` at appropriate places? Open

enhancement low priority python

Difficulty 4/5 3-5 days Newbie friendliness 48/100

ml-explore/mlx#4428 · 3 comments · Opened Aug 29, 2026
mlx_lm.server: per-request chat_template_kwargs bypasses the prompt cache (0.31.3) Open

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

ml-explore/mlx-lm#1803 · Opened Aug 29, 2026
mlx_lm.server: streamed generations do not store prompt-cache entries (0.31.3) Open

Difficulty 3/5 1-2 days Newbie friendliness 55/100

ml-explore/mlx-lm#1802 · Opened Aug 29, 2026
[BUG] metal kernels should always have a plain mlx fallback for future cuda path Open

Difficulty 4/5 3-5 days Newbie friendliness 48/100

ml-explore/mlx-swift-lm#588 · 1 comment · Opened Aug 28, 2026
Missing support for meituan-longcat/LongCat-Flash-Lite-Sparse Open

Difficulty 3/5 1-2 days Newbie friendliness 48/100

ml-explore/mlx-lm#1794 · Opened Aug 27, 2026

Showing the newest 100

This page lists what was indexed most recently. Advanced filter has the whole inventory, narrowed by language, difficulty and how long a task takes.

Open advanced filter

ml-explore

Showing the newest 100

Get new issues in your inbox