tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-09-07 07:29:39 -04:00
Code Issues Packages Projects Releases Wiki Activity

CUDA: use mma PTX instructions for FlashAttention (#11583)

Browse Source 
* CUDA: use mma PTX instructions for FlashAttention

* __shfl_sync workaround for movmatrix

* add __shfl_sync to HIP

Co-authored-by: Diego Devesa <slarengh@gmail.com>
This commit is contained in:
Johannes Gäßler
2025-02-02 19:31:09 +01:00
committed by GitHub
parent 84ec8a58f7
commit 864a0b67a6
29 changed files with 2058 additions and 998 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
ggml/src/ggml-cuda/CMakeLists.txt
View File

@@ -28,7 +28,7 @@ if (CUDAToolkit_FOUND)
list(APPEND GGML_HEADERS_CUDA "../../include/ggml-cuda.h")
file(GLOB GGML_SOURCES_CUDA "*.cu")
file(GLOB SRCS "template-instances/fattn-wmma*.cu")
file(GLOB SRCS "template-instances/fattn-mma*.cu")
list(APPEND GGML_SOURCES_CUDA ${SRCS})
file(GLOB SRCS "template-instances/mmq*.cu")
list(APPEND GGML_SOURCES_CUDA ${SRCS})