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>
This commit is contained in:
Awni Hannun
2024-02-14 14:04:25 -08:00
committed by GitHub
parent 1a48713d32
commit ccf1645995
18 changed files with 624 additions and 70 deletions

View File

@@ -11,6 +11,7 @@ target_sources(
${CMAKE_CURRENT_SOURCE_DIR}/primitives.cpp
${CMAKE_CURRENT_SOURCE_DIR}/quantized.cpp
${CMAKE_CURRENT_SOURCE_DIR}/reduce.cpp
${CMAKE_CURRENT_SOURCE_DIR}/rope.cpp
${CMAKE_CURRENT_SOURCE_DIR}/scan.cpp
${CMAKE_CURRENT_SOURCE_DIR}/softmax.cpp
${CMAKE_CURRENT_SOURCE_DIR}/sort.cpp