Skip to content
GitLab
Menu
Projects
Groups
Snippets
Loading...
Help
Help
Support
Community forum
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in / Register
Toggle navigation
Menu
Open sidebar
OpenDAS
ollama
Commits
5f73c087
Unverified
Commit
5f73c087
authored
Apr 25, 2024
by
Roy Yang
Committed by
GitHub
Apr 25, 2024
Browse files
Remove trailing spaces (#3889)
parent
f503a848
Changes
2
Hide whitespace changes
Inline
Side-by-side
Showing
2 changed files
with
4 additions
and
4 deletions
+4
-4
llm/generate/gen_common.sh
llm/generate/gen_common.sh
+1
-1
llm/generate/gen_linux.sh
llm/generate/gen_linux.sh
+3
-3
No files found.
llm/generate/gen_common.sh
View file @
5f73c087
...
...
@@ -21,7 +21,7 @@ init_vars() {
# TODO - add additional optimization flags...
CMAKE_DEFS
=
"-DCMAKE_BUILD_TYPE=Release -DLLAMA_SERVER_VERBOSE=off
${
CMAKE_DEFS
}
"
fi
case
$(
uname
-s
)
in
case
$(
uname
-s
)
in
"Darwin"
)
LIB_EXT
=
"dylib"
WHOLE_ARCHIVE
=
"-Wl,-force_load"
...
...
llm/generate/gen_linux.sh
View file @
5f73c087
...
...
@@ -165,11 +165,11 @@ if [ -d "${CUDA_LIB_DIR}" ]; then
fi
if
[
"
${
ARCH
}
"
==
"arm64"
]
;
then
echo
"ARM CPU detected - disabling unsupported AVX instructions"
# ARM-based CPUs such as M1 and Tegra do not support AVX extensions.
#
# CUDA compute < 6.0 lacks proper FP16 support on ARM.
# Disabling has minimal performance effect while maintaining compatibility.
# CUDA compute < 6.0 lacks proper FP16 support on ARM.
# Disabling has minimal performance effect while maintaining compatibility.
ARM64_DEFS
=
"-DLLAMA_AVX=off -DLLAMA_AVX2=off -DLLAMA_AVX512=off -DLLAMA_CUDA_F16=off"
fi
# Users building from source can tune the exact flags we pass to cmake for configuring llama.cpp
...
...
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
.
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment