summaryrefslogtreecommitdiff
path: root/candle-metal-kernels
Commit message (Expand)AuthorAgeFilesLines
* Sync upstream MLX sdpa vector kernels with mask (#2718)HEADmainEric Buehler2025-01-162-28/+412
* Bump the caret version to 0.8.2. (#2703)Laurent Mazare2025-01-071-1/+1
* Bump the crate version to 0.8.1. (#2662)Laurent Mazare2024-12-071-1/+1
* add scatter add (#2656)zachcp2024-12-011-0/+1
* add u32 - U32 gather (#2653)zachcp2024-11-301-79/+80
* Lint fixes introduced with Rust 1.83 (#2646)Anubhab Bandyopadhyay2024-11-282-17/+20
* Add some missing index-select metal kernels. (#2613)Laurent Mazare2024-11-121-0/+4
* Bump the crate version to 0.8.0. (#2612)Laurent Mazare2024-11-121-1/+1
* Add some fast Metal MLX SDPA kernels (#2584)Eric Buehler2024-11-052-1/+1579
* UG metal integration. (#2580)Laurent Mazare2024-10-272-8/+4
* Tweak some metal tests. (#2528)Laurent Mazare2024-10-022-62/+23
* Efficient implementation of `Tensor::ones()` for `metal` (#2512)Anubhab Bandyopadhyay2024-10-013-0/+132
* Bump the crate version to 0.7.2. (#2517)Laurent Mazare2024-09-291-1/+1
* Move the candle version to 0.7.1. (#2495)Laurent Mazare2024-09-221-1/+1
* Bump the crate version. (#2491)Laurent Mazare2024-09-211-1/+1
* Bugfix for the metal elu kernel. (#2490)Laurent Mazare2024-09-211-1/+1
* Metal commands refactoring (#2489)Laurent Mazare2024-09-211-5/+28
* Fix for metal tanh. (#2475)Laurent Mazare2024-09-131-3/+8
* Add some metal gemm benchark. (#2471)Laurent Mazare2024-09-112-0/+138
* Integrate the MLX gemm kernels (#2468)Laurent Mazare2024-09-115-55/+1874
* Bump the version to 0.6.1. (#2438)Laurent Mazare2024-08-221-1/+1
* Revert the bf16 gemm metal changes for now. (#2386)Laurent Mazare2024-08-012-19/+21
* Metal bgemm min changes (#2364)ivarflakstad2024-08-013-4/+76
* Enable the affine kernel for u8/u32. (#2376)Laurent Mazare2024-08-011-0/+2
* Use RAII for terminating the encoding. (#2353)Laurent Mazare2024-07-242-61/+69
* Use a trait for the encoder provider (so that encoder can ultimately be reuse...Laurent Mazare2024-07-242-120/+143
* Bump the crate version. (#2248)Laurent Mazare2024-06-051-1/+1
* add where_cond f32 for metal (#2236)Lionel Touati2024-06-021-0/+21
* Add a metal kernel for col2im1d. (#2214)Laurent Mazare2024-05-252-1/+97
* Add the layernorm specialized op. (#2212)Laurent Mazare2024-05-242-0/+144
* Add some missing where-cond kernels for metal. (#2203)Laurent Mazare2024-05-221-14/+17
* Separate quantized phi-3 implementation. (#2157)Laurent Mazare2024-05-041-1/+1
* Bump the version number to 0.5.1. (#2155)Laurent Mazare2024-05-031-1/+1
* Fix sigmoid gradient calculation and move sigmoid into a specialized op (#2114)MilkFather2024-04-292-1/+6
* Add argsort. (#2132)Laurent Mazare2024-04-273-0/+138
* Metal Unary: Add benchmarks and process kernels in a tile based fashion (#2056)Thomas Santerre2024-04-212-37/+97
* Handle multiple dimensions in metal QMM + two fixes. (#2097)Laurent Mazare2024-04-201-7/+8
* Add missing bfloat unary strided kernels and fix typo (#2058)ivarflakstad2024-04-141-1/+1
* Support gather on bf16 for metal. (#2035)Laurent Mazare2024-04-101-0/+3
* Use BufferOffset in metal backend ops. (#2029)Laurent Mazare2024-04-082-128/+78
* Rework the buffer offset logic for metal kernels (#2028)Laurent Mazare2024-04-073-247/+262
* Optimize copy-2d for metal. (#2024)Laurent Mazare2024-04-072-20/+57
* Add the rope THD kernel. (#2014)Laurent Mazare2024-04-052-4/+89
* Add support for "sign" on tensors (#2012)Thomas Santerre2024-04-042-1/+3
* update dtypes checks for several metal operations (#2010)Thomas Santerre2024-04-042-6/+20
* Bumping the version number to 0.5.0. (#2009)Laurent Mazare2024-04-041-1/+1
* Minor cleanups in reduce.metal. (#2004)Laurent Mazare2024-04-041-23/+1
* refactor to reduce the amount of code wrapped in template syntax (#2002)Thomas Santerre2024-04-041-261/+368
* Fix for the RWKV models. (#1955)Laurent Mazare2024-03-281-4/+4
* Support i64 in index-select on metal. (#1951)Laurent Mazare2024-03-271-1/+7
generated by cgit v1.2.3 (git 2.39.1) at 2025-04-02 17:18:20 +0000