d96a2bdf57
Fix python package install path in stubgen ( #3009 )
2026-01-19 09:34:02 +09:00
ca14d3d835
Fix sharding of quantized models with non-power-of-2 bits ( #3006 )
2026-01-18 07:21:56 -08:00
d2bef3c6bb
fix distributed all_to_sharded bias shard axis from -2 to -1 ( #2987 )
2026-01-17 06:51:42 -08:00
3fe7794f22
Reverts changing the MLX_IBV_DEVICES to MLX_JACCL_DEVICES ( #2999 )
2026-01-14 15:44:17 -08:00
2469fc2939
patch bump for next release ( #2991 )
2026-01-14 08:46:09 -08:00
099dcc0f4c
Expose to/from fp8 in Python and don't auto-convert fp8 when loading from safetensors ( #2985 )
2026-01-13 15:48:21 -08:00
4160ec10f7
Fix RandomBits::is_equivalent to include width ( #2978 )
...
Co-authored-by: KD2YCU <me@kd2ycu.com >
Co-authored-by: Angelos Katharopoulos <katharas@gmail.com >
Co-authored-by: Awni Hannun <awni@apple.com >
2026-01-13 12:42:37 -08:00
a8197795f5
replace MLX_IBV_COORDINATOR with MLX_JACCL_COORDINATOR ( #2986 )
2026-01-13 11:26:25 -08:00
7b1c46982a
fix doc ( #2988 )
2026-01-12 13:33:26 -08:00
edab937248
Add asarray to __array_namespace__ ( #2966 )
2026-01-12 06:16:27 -08:00
503731727d
QQ linear ( #2931 )
2026-01-05 11:20:54 -08:00
1680b6fe38
fix numpy dtype bug ( #2960 )
2026-01-05 11:20:40 -08:00
1df6c2a009
Fix doc issues in mlx.nn.init.he_normal and mlx.nn.hard_tanh ( #2968 )
...
Co-authored-by: Awni Hannun <awni@apple.com >
2026-01-05 07:23:41 -08:00
26dfe4f651
Fetch nanobind with cmake ( #2949 )
2025-12-24 10:23:45 +09:00
1d21d0e696
[CUDA] Implement gather_mm_rhs ( #2902 )
2025-12-24 09:42:56 +09:00
1eef1d155c
Metal/CPU nvfp4 and mxfp8 ( #2946 )
2025-12-22 20:45:19 -08:00
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
Cheng