vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

ggml : move CPU backend to a separate file (#10144)

Browse source
This commit is contained in:
Diego Devesa 2024-11-03 19:34:08 +01:00 • committed by GitHub
parent 08828a6d7d
commit 9f40989351
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
32 changed files with 14747 additions and 19345 deletions
Download patch file Download diff file Expand all files Collapse all files

2
common/CMakeLists.txt
View file

@ -66,8 +66,6 @@ add_library(${TARGET} STATIC
ngram-cache.h
sampling.cpp
sampling.h
train.cpp
train.h
)
if (BUILD_SHARED_LIBS)