Skip to content

Pull requests: ml-explore/mlx

New pull request New
45 Open 1,925 Closed
45 Open 1,925 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
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

Add 1-bit affine quantization support (Metal)
#3161 opened Feb 24, 2026 by khosravipasha Loading…
4 tasks done
1
[CUDA] FPxINT quantized matmul for Hopper
#3160 opened Feb 23, 2026 by zcbenz Loading…
1
Add Expert Parallelism for MoE inference
#3158 opened Feb 23, 2026 by 0xDaizz Loading…
4 of 6 tasks
2
[WIP] columnwise quantize with tma
#3157 opened Feb 23, 2026 by nastya236 • Draft
feat: native i0 (modified Bessel function) and kaiser window
#3156 opened Feb 22, 2026 by Vlor999 Loading…
4 tasks done
feat: adding the bartlett function
#3155 opened Feb 22, 2026 by Vlor999 Loading…
4 tasks done
[JACCL] Fix silent data corruption from unchecked RDMA work completion status
#3152 opened Feb 21, 2026 by 0xDaizz Loading…
2
[CUDA] Implement MaskedScatter
#3151 opened Feb 20, 2026 by Lyxot Loading…
3 of 4 tasks
1
Fix np bfloat16 misinterpreted as complex
#3146 opened Feb 19, 2026 by kellen-sun Loading…
3 of 4 tasks
1
2
fix: use DSB SY barrier and system-scope atomic load in fence for RDMA GPU visibility
#3141 opened Feb 18, 2026 by vskiwi Loading…
5
Add recurrent SNN docs, tests, and benchmark scaffold
#3140 opened Feb 18, 2026 by Ikaikaalika Loading…
feat: implement mlx.core.blackman
#3136 opened Feb 16, 2026 by Vlor999 Loading…
4 tasks done
3
[CUDA] Fsdp (easy)
#3130 opened Feb 14, 2026 by nastya236 Loading…
1
[Metal][Performance]: Add split-K for quantized matmul (small M)
#3120 opened Feb 12, 2026 by Ziqiao-git Loading…
3 of 4 tasks
4
[CUDA][Performance] Add radix select implementation for efficient partition operations
#3117 opened Feb 9, 2026 by Lyxot Loading…
3 of 4 tasks
19
Prevent allocator from operating on residency set during metal capture
#3114 opened Feb 8, 2026 by robertmsale • Draft
3 of 4 tasks
6
PR 3103 Updating Documentation
#3104 opened Feb 6, 2026 by MillaFleurs Loading…
4 tasks done
5
Proposal to add dynamic backends to MLX
#3098 opened Feb 5, 2026 by dhiltgen Loading…
1 of 4 tasks
2
Add bounds checking on GPU
#3091 opened Feb 2, 2026 by nhey • Draft
3 of 4 tasks
2
[WIP] Fuse into reduction
#3090 opened Feb 2, 2026 by nastya236 • Draft
[Metal] [Performance] RNN speedup
#3089 opened Feb 2, 2026 by guillaume-osmo Loading…
3 of 4 tasks
1
tests: harden memory leak check in test_siblings_without_eval
#3088 opened Feb 1, 2026 by booxter Loading…
2 of 4 tasks
2
Add tiled unfolding to fix Metal maxBufferLength failures in conv_transpose
#3084 opened Jan 29, 2026 by itsmedonttell Loading…
1
[Metal] [Performance] Add radix select implementation for efficient partition operations
#3069 opened Jan 27, 2026 by NripeshN Loading…
28
Fix double precision for exp, sin, cos, erf, erfinv on CPU
#3058 opened Jan 24, 2026 by Anri-Lombard Loading…
4 tasks done
1
6
ProTip! Filter pull requests by the default branch with base:main.