-
Notifications
You must be signed in to change notification settings - Fork 2.3k
Pull requests: ml-explore/mlx
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
fix(reduce): support 64-bit indexing for reductions on views past 2^31 and large arrays
#4549
opened Sep 23, 2026 by
nicoloangileri
Loading…
1 task done
Add fused Metal cross entropy kernel
await response
This pull request is waiting for response from the author.
#4545
opened Sep 22, 2026 by
DIvkov575
Loading…
Fixes grouped Conv1d/Conv2d init to use in_channels // groups
#4544
opened Sep 22, 2026 by
CodeWithMoin
Loading…
Fix/split data size span
await verification
This pull request is non-trivial and requires a human expert to verify its correctness.
#4540
opened Sep 21, 2026 by
michalk8
Collaborator
Loading…
Add C++ linear SVM training example with automatic differentiation
#4537
opened Sep 20, 2026 by
StarxSky
Loading…
Fix CustomKernel Metal dispatch silently truncating the requested threadgrid
#4535
opened Sep 19, 2026 by
pseudobacon
Loading…
Advances file offset during partial reads and adds EOF/signal handling in ParallelFileReader::read #4526
#4532
opened Sep 18, 2026 by
Ritabanm
Contributor
Loading…
1 task done
fix(CUDA): Do not throw from ~CudaHandle while the driver is unloading
#4531
opened Sep 18, 2026 by
inureyes
Loading…
Report a dead peer in JACCL instead of spinning forever; name the lin…
low priority
#4530
opened Sep 18, 2026 by
Sofille65
Loading…
Fix
col_reduce_longcolumn for negative-stride views
low priority
#4529
opened Sep 17, 2026 by
mateuuszzzzz
Loading…
Fix default.metallib lookup under swift test with Swift Build
low priority
#4527
opened Sep 17, 2026 by
heckj
Contributor
Loading…
Clear CUDA errors once reported and raise eval errors in buffer protocol
low priority
#4523
opened Sep 16, 2026 by
aleroot
Contributor
Loading…
Add fused Metal kernels for fast.cross_entropy
await verification
This pull request is non-trivial and requires a human expert to verify its correctness.
#4520
opened Sep 16, 2026 by
zsun6
Loading…
Fix ordering of complex64 with NaNs
low priority
#4519
opened Sep 15, 2026 by
louen
Contributor
Loading…
fix(cpu): use size_t for contiguous binary op element counts (#4479)
low priority
#4517
opened Sep 15, 2026 by
Prudctual
Loading…
Use the fast qmv kernel for affine outputs not divisible by 8
low priority
#4516
opened Sep 15, 2026 by
wyanzhao
Contributor
Loading…
Fix CUDA termination crash via deterministic worker teardown and lazy stream evaluation
#4514
opened Sep 15, 2026 by
aleroot
Contributor
Loading…
Clamp slice bounds when a slice is combined with an array index
low priority
#4513
opened Sep 15, 2026 by
IshaanPotle
Loading…
Fix floating-point constant precision in compiled kernels
low priority
#4511
opened Sep 15, 2026 by
Ryan11c
Loading…
Support shapeless compilation of scan operations
low priority
#4510
opened Sep 15, 2026 by
keeeeenw
Loading…
[CUDA] Add fp_gather_qmv to optimize gather_qmm
await response
This pull request is waiting for response from the author.
#4508
opened Sep 14, 2026 by
dhiltgen
Contributor
Loading…
Previous Next
ProTip!
Mix and match filters to narrow down what you’re looking for.