zhangyiss/mlx
1
0
Fork 0
mirror of https://github.com/ml-explore/mlx.git synced 2025-07-19 15:41:13 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity
ccf1645995
mlx/mlx/backend/metal/kernels
History
Awni Hannun ccf1645995
Custom primitive + RoPE fat op (#676) 
* extensions start

* rope custom op

* fix build

* docs + rope benchmark

* fix test

* Add a Metal kernel for RoPE

* Fix position of traditional

* transform tests

* Move rope computation to float and fix tests

* Fix the test and a typo

* change to fast

* fix no metal build

---------

Co-authored-by: Angelos Katharopoulos <a_katharopoulos@apple.com>
2024-02-14 14:04:25 -08:00
..
steel Remove masks from BlockLoader and clear out load case for invalid thread (#634) 2024-02-05 16:00:17 -08:00
arange.metal copyright + ack 2023-11-30 11:12:53 -08:00
arg_reduce.metal Add GPU support for uint64/int64 reductions (#569) 2024-01-31 11:18:04 -08:00
atomic.h Fix eye for larger matrices (#463) 2024-01-16 00:51:24 -08:00
bf16_math.h copyright + ack 2023-11-30 11:12:53 -08:00
bf16.h copyright + ack 2023-11-30 11:12:53 -08:00
binary_two.metal Remainder negative numerator bug fixed (#641) 2024-02-09 16:49:14 -08:00
binary.h Remainder negative numerator bug fixed (#641) 2024-02-09 16:49:14 -08:00
binary.metal Kernel generation (#614) 2024-02-07 13:15:59 -08:00
CMakeLists.txt Custom primitive + RoPE fat op (#676) 2024-02-14 14:04:25 -08:00
compiled_preamble.h Kernel generation (#614) 2024-02-07 13:15:59 -08:00
complex.h Remainder negative numerator bug fixed (#641) 2024-02-09 16:49:14 -08:00
conv_params.h copyright + ack 2023-11-30 11:12:53 -08:00
conv.h Update GEMM (#424) 2024-01-17 12:42:39 -08:00
conv.metal Update GEMM (#424) 2024-01-17 12:42:39 -08:00
copy.metal copyright + ack 2023-11-30 11:12:53 -08:00
defines.h copyright + ack 2023-11-30 11:12:53 -08:00
erf.h copyright + ack 2023-11-30 11:12:53 -08:00
gather.metal Update gather and scatter to not use Argument Encoder (#683) 2024-02-14 13:42:13 -08:00
gemv.metal Fix oob reads in gemv kernel (#523) 2024-01-22 12:06:04 -08:00
indexing.h Update gather and scatter to not use Argument Encoder (#683) 2024-02-14 13:42:13 -08:00
quantized.metal Quantized matmul fix (#677) 2024-02-12 18:54:21 -08:00
random.metal copyright + ack 2023-11-30 11:12:53 -08:00
reduce.h Fix eye for larger matrices (#463) 2024-01-16 00:51:24 -08:00
reduce.metal Add GPU support for uint64/int64 reductions (#569) 2024-01-31 11:18:04 -08:00
rope.metal Custom primitive + RoPE fat op (#676) 2024-02-14 14:04:25 -08:00
scan.metal copyright + ack 2023-11-30 11:12:53 -08:00
scatter.metal Update gather and scatter to not use Argument Encoder (#683) 2024-02-14 13:42:13 -08:00
softmax.metal copyright + ack 2023-11-30 11:12:53 -08:00
sort.metal Spelling (#342) 2024-01-01 21:08:17 -08:00
unary.h Kernel generation (#614) 2024-02-07 13:15:59 -08:00
unary.metal Kernel generation (#614) 2024-02-07 13:15:59 -08:00
utils.h Faster gather and scatter. (#682) 2024-02-13 17:47:41 -08:00