Skip to content

Pull requests: ml-explore/mlx

New pull request New
50 Open 2,029 Closed
50 Open 2,029 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

fix: fail build when Metal compiler header resolution fails
#3332 opened Mar 29, 2026 by dogukanveziroglu Loading…
2 of 4 tasks
chore: update copyright year to 2026
#3331 opened Mar 29, 2026 by Jack-sh1 Loading…
3 of 4 tasks
Add TurboQuant KV cache compression with native Metal SDPA kernel
#3328 opened Mar 28, 2026 by arozanov Loading…
4 tasks done
Remove no longer needed const_cast
#3325 opened Mar 26, 2026 by zcbenz Loading…
[CUDA] Add GatherQMM for quantized gather matmul
#3321 opened Mar 25, 2026 by Lyxot Loading…
12
Implement BroadcastAxes::vmap
#3319 opened Mar 25, 2026 by Aristide021 Loading…
3
fix: defer error propagation from Metal completion handlers
#3318 opened Mar 25, 2026 by Thump604 Loading…
1
6
Decouple CommandEncoder from Device
#3316 opened Mar 25, 2026 by zcbenz Loading…
[CUDA] Fallback QMM
#3315 opened Mar 25, 2026 by zcbenz Loading…
[Metal] Support sorting complex numbers
#3314 opened Mar 25, 2026 by Lyxot Loading…
6
Chunked full-attention SDPA for long key sequences
#3307 opened Mar 24, 2026 by Thump604 Loading…
10 tasks done
1
3
Add logsumexp output to fused SDPA kernel
#3306 opened Mar 24, 2026 by Thump604 Loading…
8 tasks done
3
Add fftfreq, rfftfreq and scalar axes for fftshift/ifftshift
#3298 opened Mar 23, 2026 by declanhealy2 Loading…
4 tasks done
2
add nn.WeightNorm layer
#3296 opened Mar 22, 2026 by mm65x • Draft
4 tasks done
Extend regular NAX tuning to gen-17 g devices
#3295 opened Mar 22, 2026 by lentil32 Loading…
4 tasks done
fix: add head_dim=256 to fused SDPA full attention kernel
#3293 opened Mar 22, 2026 by Thump604 Loading…
15
add causal_upper_left mask option to scaled_dot_product_attention
#3254 opened Mar 14, 2026 by mm65x Loading…
4 tasks done
1
[Metal] Fused Flash Attention backward (VJP) kernels
#3241 opened Mar 11, 2026 by Brooooooklyn Loading…
1
Add bias support to QQLinear
#3215 opened Mar 6, 2026 by mdepree Loading…
4 tasks done
6
Fix shapeless compile eliding reductions on size-1 dimensions
#3202 opened Mar 4, 2026 by ghstrider Loading…
1
2
Add bessel_i0e and bessel_i1e ops
#3193 opened Mar 3, 2026 by robert-johansson Loading…
2 of 3 tasks
Fix command buffer memory tracking to use bytes instead of elements
#3192 opened Mar 3, 2026 by hxu296 Loading…
3 of 4 tasks
2
Add lgamma and digamma ops
#3181 opened Feb 27, 2026 by robert-johansson Loading…
3 of 4 tasks
1
Add all_to_all collective primitive
#3164 opened Feb 24, 2026 by 0xDaizz Loading…
2 of 4 tasks
1
Add Expert Parallelism for MoE inference
#3158 opened Feb 23, 2026 by 0xDaizz • Draft
1 of 7 tasks
3
ProTip! Type g i on any issue or pull request to go back to the issue listing page.