L-electron-Rare/mlx
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
1,631 Commits 15 Branches 83 Tags
1d56dfdf596c0c7d8fc026aa8eef26d9476ccf47
Commit Graph

841 Commits

Author SHA1 Message Date
Awni Hannun 1d56dfdf59 Use higher precision for linspace with double (#3029) 2026-01-21 06:20:50 -08:00
XXXXRT666 46d0fdc5ec Type Enhancement for Func Transforms and Bug Fix (#3003) 
Co-authored-by: Awni Hannun <awni@apple.com>
 2026-01-20 07:19:57 +09:00
Cheng d96a2bdf57 Fix python package install path in stubgen (#3009) 2026-01-19 09:34:02 +09:00
Tarjei Mandt ca14d3d835 Fix sharding of quantized models with non-power-of-2 bits (#3006) 2026-01-18 07:21:56 -08:00
gufengc d2bef3c6bb fix distributed all_to_sharded bias shard axis from -2 to -1 (#2987) 2026-01-17 06:51:42 -08:00
Angelos Katharopoulos 3fe7794f22 Reverts changing the MLX_IBV_DEVICES to MLX_JACCL_DEVICES (#2999) 2026-01-14 15:44:17 -08:00
Awni Hannun 2469fc2939 patch bump for next release (#2991) 2026-01-14 08:46:09 -08:00
Awni Hannun 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
MillaFleurs 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
Evan Quiney a8197795f5 replace MLX_IBV_COORDINATOR with MLX_JACCL_COORDINATOR (#2986) 2026-01-13 11:26:25 -08:00
CCYeh 7b1c46982a fix doc (#2988) 2026-01-12 13:33:26 -08:00
Anri Lombard edab937248 Add asarray to __array_namespace__ (#2966) 2026-01-12 06:16:27 -08:00
Anastasiia Filippova 503731727d QQ linear (#2931) 2026-01-05 11:20:54 -08:00
Awni Hannun 1680b6fe38 fix numpy dtype bug (#2960) 2026-01-05 11:20:40 -08:00
1ndig0 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
Cheng 26dfe4f651 Fetch nanobind with cmake (#2949) 2025-12-24 10:23:45 +09:00
Cheng 1d21d0e696 [CUDA] Implement gather_mm_rhs (#2902) 2025-12-24 09:42:56 +09:00
Awni Hannun 1eef1d155c Metal/CPU nvfp4 and mxfp8 (#2946) 2025-12-22 20:45:19 -08:00
Angelos Katharopoulos 9cfda1a86e Fixes in mlx.distributed_config (#2947) 2025-12-22 17:38:52 -08:00
Awni Hannun c0fea26ed2 Fix for non row-contig scales (#2941) 2025-12-21 06:12:41 -08:00
Angelos Katharopoulos d9f4d8d508 Fix pid in local launch (#2936) 2025-12-19 13:09:15 -08:00
Cheng fc19a08caa Set install rpath of python bindings with cmake (#2934) 2025-12-19 16:43:00 +09:00
Cheng b2e2b19bf7 Set rpath with cmake for CUDA build (#2932) 2025-12-19 12:53:38 +09:00
Angelos Katharopoulos 9194ec20a8 Thunderbolt RDMA communications backend (#2808) 2025-12-17 11:27:54 -08:00
Anastasiia Filippova 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
Awni Hannun 81dfe5f137 Fix grad in place updates (#2899) 2025-12-11 14:44:58 -08:00
Nathan Goldbaum e1fee0074b Update nanobind pin to most recent version (#2896) 2025-12-11 06:07:36 -08:00
CCYeh 3c8ce9b00e Fix input buffer donation in compile (#2897) 2025-12-11 06:07:03 -08:00
Angelos Katharopoulos 997cfc7699 Add a 2-pass col reduce for CUDA (#2863) 2025-12-04 15:53:59 -08:00
Awni Hannun 1fa8dc5797 Do a PyPi release for cuda on arm (#2866) 2025-12-04 15:28:29 -08:00
Awni Hannun a6d6717181 fix compile copying (#2871) 2025-12-04 12:32:56 -08:00
Awni Hannun 941cfe23d7 Layer norm throws on dimension mismatch (#2870) 2025-12-04 11:21:05 -08:00
romanoneg 9abb0b8123 Added support for pytree types that inherit from tuple and typing.namedtuple (#2845) 2025-12-04 11:06:45 -08:00
Tian En "TianHeng 50d3914c67 Update gumbel function signature parameters (#2868) 2025-12-03 15:37:35 -08:00
Awni Hannun cacbdbf995 Fix init from double (#2861) 2025-12-03 06:08:11 -08:00
Awni Hannun d8ceae7b77 Reduce JVP (#2854) 2025-12-02 16:17:47 -08:00
Awni Hannun eff0e31f00 Fix export scatters (#2852) 2025-12-02 11:24:40 -08:00
CCYeh 8879ee00eb Support more Numpy interfaces for masked_scatter (#2832) 2025-12-01 17:51:02 -08:00
Chaoran Yu 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
Cheng 704fd1ae28 [CUDA] Support array mask in SDPA (#2822) 2025-11-26 11:08:58 +09:00
CCYeh 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
CCYeh 5b0f047226 Fix mx.core.load type annotation (#2819) 2025-11-22 11:09:44 -08:00
Harsh Sutaria 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
Awni Hannun 4a09264236 Tolerance for some ops tests on cuda (#2815) 2025-11-21 16:06:16 -08:00
Jagrit Digani 54f1cc6e3e Add Neural Accelerator Support (#2772) 2025-11-19 15:06:00 -08:00
CCYeh 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
Awni Hannun f46877bc08 more accurate rope fallback (#2792) 2025-11-19 06:07:21 -08:00
Cheng 6f35017d1b [CUDA] cuDNN backward attention (#2762) 2025-11-19 08:13:50 +09:00
Cheng 32b18d8b66 Use std::optional for mask_arr arg (#2763) 2025-11-17 10:43:33 +09:00
Awni Hannun 27ff069175 Fix exporting with constants (#2769) 2025-11-14 12:52:08 -08:00