9cfda1a86e
Fixes in mlx.distributed_config ( #2947 )
2025-12-22 17:38:52 -08:00
c0fea26ed2
Fix for non row-contig scales ( #2941 )
2025-12-21 06:12:41 -08:00
d9f4d8d508
Fix pid in local launch ( #2936 )
2025-12-19 13:09:15 -08:00
fc19a08caa
Set install rpath of python bindings with cmake ( #2934 )
2025-12-19 16:43:00 +09:00
b2e2b19bf7
Set rpath with cmake for CUDA build ( #2932 )
2025-12-19 12:53:38 +09:00
9194ec20a8
Thunderbolt RDMA communications backend ( #2808 )
2025-12-17 11:27:54 -08:00
4cf5b29fc5
qqmm ( #2789 )
...
Co-authored-by: root <root@bolt-t9a77vmteu-94s9t6ymth.bolt-pods.turi-bolt.svc.cluster.local >
Co-authored-by: root <root@bolt-5azkyvd8ga-kgfzk84y6m.bolt-pods.turi-bolt.svc.cluster.local >
Co-authored-by: root <root@bolt-y4nktpaecv-ssnx24rdha.bolt-pods.turi-bolt.svc.cluster.local >
2025-12-16 09:28:28 -08:00
81dfe5f137
Fix grad in place updates ( #2899 )
2025-12-11 14:44:58 -08:00
e1fee0074b
Update nanobind pin to most recent version ( #2896 )
2025-12-11 06:07:36 -08:00
3c8ce9b00e
Fix input buffer donation in compile ( #2897 )
2025-12-11 06:07:03 -08:00
997cfc7699
Add a 2-pass col reduce for CUDA ( #2863 )
2025-12-04 15:53:59 -08:00
1fa8dc5797
Do a PyPi release for cuda on arm ( #2866 )
2025-12-04 15:28:29 -08:00
a6d6717181
fix compile copying ( #2871 )
2025-12-04 12:32:56 -08:00
941cfe23d7
Layer norm throws on dimension mismatch ( #2870 )
2025-12-04 11:21:05 -08:00
9abb0b8123
Added support for pytree types that inherit from tuple and typing.namedtuple ( #2845 )
2025-12-04 11:06:45 -08:00
50d3914c67
Update gumbel function signature parameters ( #2868 )
2025-12-03 15:37:35 -08:00
cacbdbf995
Fix init from double ( #2861 )
2025-12-03 06:08:11 -08:00
d8ceae7b77
Reduce JVP ( #2854 )
2025-12-02 16:17:47 -08:00
eff0e31f00
Fix export scatters ( #2852 )
2025-12-02 11:24:40 -08:00
8879ee00eb
Support more Numpy interfaces for masked_scatter ( #2832 )
2025-12-01 17:51:02 -08:00
b054838780
Added clarification to apply_fn parameter of apply_to_modules ( #2831 )
...
Co-authored-by: Awni Hannun <awni@apple.com >
2025-11-26 15:40:56 -08:00
704fd1ae28
[CUDA] Support array mask in SDPA ( #2822 )
2025-11-26 11:08:58 +09:00
1d4eacb737
Fix mx.core.linspace type annotation ( #2820 )
...
Co-authored-by: Awni Hannun <awni.hannun@gmail.com >
2025-11-24 14:15:08 -08:00
5b0f047226
Fix mx.core.load type annotation ( #2819 )
2025-11-22 11:09:44 -08:00
618c87af8c
Add float64 Eig and complex64 SVD/Eig support ( Fixes #2708 ) ( #2737 )
...
Co-authored-by: Awni Hannun <awni.hannun@gmail.com >
Co-authored-by: Awni Hannun <awni@apple.com >
2025-11-22 06:51:36 -08:00
4a09264236
Tolerance for some ops tests on cuda ( #2815 )
2025-11-21 16:06:16 -08:00
54f1cc6e3e
Add Neural Accelerator Support ( #2772 )
2025-11-19 15:06:00 -08:00
b3825ac149
Add Masked Scatter ( #2663 )
...
Co-authored-by: Awni Hannun <awni@apple.com >
Co-authored-by: Angelos Katharopoulos <katharas@gmail.com >
Co-authored-by: Angelos Katharopoulos <a_katharopoulos@apple.com >
2025-11-19 14:53:32 -08:00
f46877bc08
more accurate rope fallback ( #2792 )
2025-11-19 06:07:21 -08:00
6f35017d1b
[CUDA] cuDNN backward attention ( #2762 )
2025-11-19 08:13:50 +09:00
32b18d8b66
Use std::optional for mask_arr arg ( #2763 )
2025-11-17 10:43:33 +09:00
27ff069175
Fix exporting with constants ( #2769 )
2025-11-14 12:52:08 -08:00
3b2ffcefc3
[CUDA] cuDNN forward attention ( #2743 )
...
* Separate sdpa kernels in another file
* Initial support for cuDNN SDPA
* Diable a few corner cases
* Remove scaled_dot_product_attention.h
* Use cuDNN attention for prefilling
* cuDNN SDPA requires Ampere and later
* Address reviews
* Do contiguous copy of inputs
2025-11-14 09:23:56 +09:00
66519fb348
fix slice ( #2758 )
2025-11-13 11:30:02 -08:00
8973550ff3
export custom kernel ( #2756 )
2025-11-13 11:29:50 -08:00
23f81ed1c1
Linux on arm ( #2751 )
...
* try linux on arm
* ssh
* fix
2025-11-11 11:41:14 -08:00
9320eb89a8
Fix dequantize python sig (dtype default) ( #2752 )
2025-11-11 09:55:24 -08:00
eba6a9d163
Compatibility with pip-installed openmpi ( #2741 )
2025-11-07 16:58:31 -08:00
be9e2aebd6
Shapeless support for zeros/ones_like ( #2726 )
...
* shapeless support for zeros/ones_like
* Improvements
* fix access after moved
2025-11-06 19:12:20 -08:00
27778156dc
Nccl reduce scatter, all gather ( #2727 )
...
* Added reduce scatter and all gather for nccl
* fix unused import, delete unused file
* small fix
* deleted useless condition
* fixed comments
* fix bug in eval_gpu, renamed to sum_scatter, fix docs
* final fix docs
* remove and
* Update mlx/distributed/mpi/mpi.cpp
Co-authored-by: Awni Hannun <awni.hannun@gmail.com >
* fix broken set input output
* fixes set output
* typo
* fix typo
* no cpu, no gpu for reduce scatter
---------
Co-authored-by: Awni Hannun <awni.hannun@gmail.com >
2025-11-05 08:21:11 -08:00
26ceb507eb
only build for macos 14 and up ( #2731 )
...
* only build for macos 14 and up
* bump metal cpp
2025-11-04 09:44:15 -08:00
50fa315d18
Fix addmm with empty matrices and beta != 1.0 ( #2715 )
2025-11-03 14:16:15 -08:00
93d76b0f30
Fix compile multi capture ( #2678 )
...
* fix compile when compiling multiple lambdas with the same capture
* add test
2025-11-03 06:33:43 -08:00
b901a9f311
Fix the order of hosts in the ring ( #2718 )
2025-10-30 15:02:39 -07:00
68c5fa1c95
fix memory count bug ( #2717 )
2025-10-30 14:27:15 -07:00
793a31eeb6
Fix missing domain_uuid_key in thunderbolt ring setup ( #2682 )
2025-10-30 13:17:20 -07:00
ec72b44417
Add quantize/dequantize for mxfp8 and nvfp4 ( #2688 )
...
* Add quantize/dequantize slow path for mxfp8 and nvfp4
* fast cuda kernel for mx/nv quantization
* fallback for cuda < 12.8 (#2697 )
* format (#2700 )
* fix (#2701 )
* metal kernels
* docs
* fix jit
* add default bits and group sizes
* improve quant docs
* fix output type of mxfp4 matmuls
2025-10-28 16:23:12 -07:00
539d8322d1
add median op ( #2705 )
2025-10-27 11:33:42 -07:00
c4767d110f
fix addmm cpu ( #2699 )
2025-10-27 11:33:32 -07:00
233384161e
Improved mx.split() docs ( #2689 )
...
* Improved mx.split() documentation
* Fix typo in docstring for array split function
* add example
---------
Co-authored-by: Awni Hannun <awni@apple.com >
2025-10-24 09:48:41 -07:00
Angelos Katharopoulos