4e00919e5c
[CUDA][NCCL] group split ( #3172 )
2026-02-26 09:26:20 +01:00
a8ba5ac3e0
Implement mlx.core.blackman ( #3136 )
2026-02-25 13:42:40 -08:00
1d8d693d08
[Metal] Add implicit matmul pathway for mx.conv3d ( #3147 )
...
Co-authored-by: Gleb Sterkin <g_sterkin@apple.com >
Co-authored-by: Angelos Katharopoulos <a_katharopoulos@apple.com >
2026-02-23 17:52:50 -08:00
f2f2d16451
Export: preserve Dtype state values in export callback arguments ( #3145 )
...
Co-authored-by: Awni Hannun <awni@apple.com >
2026-02-19 08:07:28 -08:00
06305022ab
Tensor scale nvfp4 ( #3022 )
2026-02-18 11:19:26 +01:00
360639c2df
Add the hamming window function ( #3135 )
2026-02-17 00:56:05 -08:00
3bbe87e6dc
Add hanning window function ( #3124 )
2026-02-16 09:44:49 -08:00
e226af720e
Propagate quantization mode in quantized layers ( #3133 )
2026-02-15 18:33:13 -08:00
72e94c81e1
[CUDA] Attention sinks in cuDNN SDPA ( #3118 )
2026-02-11 16:46:39 +09:00
54bb3eea42
[CUDA] Use cuDNN SDPA for decoding when using fixed-size KV cache ( #3113 )
2026-02-10 09:15:45 +09:00
5e018de4e5
Quantize module to QQLinear ( #3106 )
2026-02-09 14:35:17 -08:00
566bc16b7c
Cleanup test_fast_sdpa.py ( #3112 )
2026-02-08 19:04:24 +09:00
90e38f7b93
Fix qmv_impl for small N ( #3096 )
2026-02-05 17:33:36 -08:00
8ef539522c
Fix failing python tests on Windows ( #3076 )
2026-01-30 17:50:18 +09:00
fcbdd05022
More useful error for large indices ( #3079 )
2026-01-29 13:02:39 -08:00
0c6a895ed7
Use lower-right causal mask alignment consistently ( #2967 )
...
Co-authored-by: Awni Hannun <awni.hannun@gmail.com >
2026-01-28 17:15:14 -08:00
4912cc47c2
Fp qmv ( #2984 )
2026-01-27 06:33:06 -08:00
a828e769be
GPU discovery ( #3055 )
...
Co-authored-by: Angelos Katharopoulos <a_katharopoulos@apple.com >
2026-01-26 09:54:13 -08:00
5bd99dd5ec
Fix flaky macOS test ( #3063 )
2026-01-25 16:40:57 -08:00
fd27829efa
Build and test python package on Windows CI ( #3049 )
2026-01-24 07:22:36 +09:00
9bac6f8584
Allow take on empty array when it makes sense ( #3046 )
2026-01-23 07:25:46 -08:00
1d56dfdf59
Use higher precision for linspace with double ( #3029 )
2026-01-21 06:20:50 -08:00
ca14d3d835
Fix sharding of quantized models with non-power-of-2 bits ( #3006 )
2026-01-18 07:21:56 -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
edab937248
Add asarray to __array_namespace__ ( #2966 )
2026-01-12 06:16:27 -08:00
1680b6fe38
fix numpy dtype bug ( #2960 )
2026-01-05 11:20:40 -08:00
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
c0fea26ed2
Fix for non row-contig scales ( #2941 )
2025-12-21 06:12:41 -08:00
81dfe5f137
Fix grad in place updates ( #2899 )
2025-12-11 14:44:58 -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
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
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
704fd1ae28
[CUDA] Support array mask in SDPA ( #2822 )
2025-11-26 11:08:58 +09:00
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
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
Anastasiia Filippova