Skip to content

Added systemd units and set versioning to use date. #2835

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 3 commits into from
Aug 28, 2023
Merged

Added systemd units and set versioning to use date. #2835

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
aeb1950
Corrections and systemd units
jboero Aug 27, 2023
6206ed6
Missing dependency clblast
jboero Aug 27, 2023
46395e6
Merge branch 'ggerganov:master' into systemd-units
jboero Aug 27, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
44 changes: 35 additions & 9 deletions .devops/lamma-cpp-clblast.srpm.spec → .devops/llama-cpp-clblast.srpm.spec
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,12 +13,13 @@
# It is up to the user to install the correct vendor-specific support.

Name: llama.cpp-clblast
Version: master
Version: %( date "+%%Y%%m%%d" )
Release: 1%{?dist}
Summary: OpenCL Inference of LLaMA model in pure C/C++
Summary: OpenCL Inference of LLaMA model in C/C++
License: MIT
Source0: https://github.com/ggerganov/llama.cpp/archive/refs/heads/master.tar.gz
BuildRequires: coreutils make gcc-c++ git mesa-libOpenCL-devel
BuildRequires: coreutils make gcc-c++ git mesa-libOpenCL-devel clblast-devel
Requires: clblast
URL: https://github.com/ggerganov/llama.cpp

%define debug_package %{nil}
Expand All @@ -35,18 +36,43 @@ make -j LLAMA_CLBLAST=1

%install
mkdir -p %{buildroot}%{_bindir}/
cp -p main %{buildroot}%{_bindir}/llamacppclblast
cp -p server %{buildroot}%{_bindir}/llamacppclblastserver
cp -p simple %{buildroot}%{_bindir}/llamacppclblastsimple
cp -p main %{buildroot}%{_bindir}/llamaclblast
cp -p server %{buildroot}%{_bindir}/llamaclblastserver
cp -p simple %{buildroot}%{_bindir}/llamaclblastsimple

mkdir -p %{buildroot}/usr/lib/systemd/system
%{__cat} <<EOF > %{buildroot}/usr/lib/systemd/system/llamaclblast.service
[Unit]
Description=Llama.cpp server, CPU only (no GPU support in this build).
After=syslog.target network.target local-fs.target remote-fs.target nss-lookup.target

[Service]
Type=simple
EnvironmentFile=/etc/sysconfig/llama
ExecStart=/usr/bin/llamaclblastserver $LLAMA_ARGS
ExecReload=/bin/kill -s HUP $MAINPID
Restart=never

[Install]
WantedBy=default.target
EOF

mkdir -p %{buildroot}/etc/sysconfig
%{__cat} <<EOF > %{buildroot}/etc/sysconfig/llama
LLAMA_ARGS="-m /opt/llama2/ggml-model-f32.bin"
EOF

%clean
rm -rf %{buildroot}
rm -rf %{_builddir}/*

%files
%{_bindir}/llamacppclblast
%{_bindir}/llamacppclblastserver
%{_bindir}/llamacppclblastsimple
%{_bindir}/llamaclblast
%{_bindir}/llamaclblastserver
%{_bindir}/llamaclblastsimple
/usr/lib/systemd/system/llamaclblast.service
%config /etc/sysconfig/llama


%pre

Expand Down
26 changes: 25 additions & 1 deletion .devops/lamma-cpp-cublas.srpm.spec → .devops/llama-cpp-cublas.srpm.spec
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,7 +13,7 @@
# It is up to the user to install the correct vendor-specific support.

Name: llama.cpp-cublas
Version: master
Version: %( date "+%%Y%%m%%d" )
Release: 1%{?dist}
Summary: CPU Inference of LLaMA model in pure C/C++ (no CUDA/OpenCL)
License: MIT
Expand All @@ -40,6 +40,28 @@ cp -p main %{buildroot}%{_bindir}/llamacppcublas
cp -p server %{buildroot}%{_bindir}/llamacppcublasserver
cp -p simple %{buildroot}%{_bindir}/llamacppcublassimple

mkdir -p %{buildroot}/usr/lib/systemd/system
%{__cat} <<EOF > %{buildroot}/usr/lib/systemd/system/llamacublas.service
[Unit]
Description=Llama.cpp server, CPU only (no GPU support in this build).
After=syslog.target network.target local-fs.target remote-fs.target nss-lookup.target

[Service]
Type=simple
EnvironmentFile=/etc/sysconfig/llama
ExecStart=/usr/bin/llamacppcublasserver $LLAMA_ARGS
ExecReload=/bin/kill -s HUP $MAINPID
Restart=never

[Install]
WantedBy=default.target
EOF

mkdir -p %{buildroot}/etc/sysconfig
%{__cat} <<EOF > %{buildroot}/etc/sysconfig/llama
LLAMA_ARGS="-m /opt/llama2/ggml-model-f32.bin"
EOF

%clean
rm -rf %{buildroot}
rm -rf %{_builddir}/*
Expand All @@ -48,6 +70,8 @@ rm -rf %{_builddir}/*
%{_bindir}/llamacppcublas
%{_bindir}/llamacppcublasserver
%{_bindir}/llamacppcublassimple
/usr/lib/systemd/system/llamacublas.service
%config /etc/sysconfig/llama

%pre

Expand Down
45 changes: 36 additions & 9 deletions .devops/llama-cpp.srpm.spec
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,47 +6,74 @@
# Notes for llama.cpp:
# 1. Tags are currently based on hash - which will not sort asciibetically.
# We need to declare standard versioning if people want to sort latest releases.
# In the meantime, YYYYMMDD format will be used.
# 2. Builds for CUDA/OpenCL support are separate, with different depenedencies.
# 3. NVidia's developer repo must be enabled with nvcc, cublas, clblas, etc installed.
# Example: https://developer.download.nvidia.com/compute/cuda/repos/fedora37/x86_64/cuda-fedora37.repo
# 4. OpenCL/CLBLAST support simply requires the ICD loader and basic opencl libraries.
# It is up to the user to install the correct vendor-specific support.

Name: llama.cpp
Version: master
Version: %( date "+%%Y%%m%%d" )
Release: 1%{?dist}
Summary: CPU Inference of LLaMA model in pure C/C++ (no CUDA/OpenCL)
License: MIT
Source0: https://github.com/ggerganov/llama.cpp/archive/refs/heads/master.tar.gz
BuildRequires: coreutils make gcc-c++ git
BuildRequires: coreutils make gcc-c++ git libstdc++-devel
Requires: libstdc++
URL: https://github.com/ggerganov/llama.cpp

%define debug_package %{nil}
%define source_date_epoch_from_changelog 0

%description
CPU inference for Meta's Lllama2 models using default options.
Models are not included in this package and must be downloaded separately.

%prep
%autosetup
%setup -n llama.cpp-master

%build
make -j

%install
mkdir -p %{buildroot}%{_bindir}/
cp -p main %{buildroot}%{_bindir}/llamacpp
cp -p server %{buildroot}%{_bindir}/llamacppserver
cp -p simple %{buildroot}%{_bindir}/llamacppsimple
cp -p main %{buildroot}%{_bindir}/llama
cp -p server %{buildroot}%{_bindir}/llamaserver
cp -p simple %{buildroot}%{_bindir}/llamasimple

mkdir -p %{buildroot}/usr/lib/systemd/system
%{__cat} <<EOF > %{buildroot}/usr/lib/systemd/system/llama.service
[Unit]
Description=Llama.cpp server, CPU only (no GPU support in this build).
After=syslog.target network.target local-fs.target remote-fs.target nss-lookup.target

[Service]
Type=simple
EnvironmentFile=/etc/sysconfig/llama
ExecStart=/usr/bin/llamaserver $LLAMA_ARGS
ExecReload=/bin/kill -s HUP $MAINPID
Restart=never

[Install]
WantedBy=default.target
EOF

mkdir -p %{buildroot}/etc/sysconfig
%{__cat} <<EOF > %{buildroot}/etc/sysconfig/llama
LLAMA_ARGS="-m /opt/llama2/ggml-model-f32.bin"
EOF

%clean
rm -rf %{buildroot}
rm -rf %{_builddir}/*

%files
%{_bindir}/llamacpp
%{_bindir}/llamacppserver
%{_bindir}/llamacppsimple
%{_bindir}/llama
%{_bindir}/llamaserver
%{_bindir}/llamasimple
/usr/lib/systemd/system/llama.service
%config /etc/sysconfig/llama

%pre

Expand Down