EngineX-Ascend/enginex-ascend-910-llama.cpp
10
0
Fork 0
Code Issues Pull Requests Actions 4 Projects Releases Wiki Activity

CUDA: faster tile FA, add oob checks, more HSs (#16492)

Browse Source
This commit is contained in:
Johannes Gäßler
2025-10-11 20:54:32 +02:00
committed by GitHub
parent a3cb04744f
commit 11f0af5504
18 changed files with 1358 additions and 784 deletions
Download Patch File Download Diff File Expand all files Collapse all files

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

@@ -44,6 +44,8 @@ if (CUDAToolkit_FOUND)
list(APPEND GGML_HEADERS_CUDA "../../include/ggml-cuda.h")
file(GLOB GGML_SOURCES_CUDA "*.cu")
file(GLOB SRCS "template-instances/fattn-tile*.cu")
list(APPEND GGML_SOURCES_CUDA ${SRCS})
file(GLOB SRCS "template-instances/fattn-mma*.cu")
list(APPEND GGML_SOURCES_CUDA ${SRCS})
file(GLOB SRCS "template-instances/mmq*.cu")