mirror of
https://github.com/mudler/LocalAI.git
synced 2025-05-23 12:05:00 +00:00
feat: llama.cpp gRPC C++ backend (#1170)
* wip: llama.cpp c++ gRPC server Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * make it work, attach it to the build process Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * update deps Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix: add protobuf dep Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * try fix protobuf on cmake * cmake: workarounds Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * add packages * cmake: use fixed version of grpc Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * cmake(grpc): install locally * install grpc Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * install required deps for grpc on debian bullseye Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * debug * debug * Fixups * no need to install cmake manually Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * ci: fixup macOS * use brew whenever possible Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * macOS fixups * debug * fix container build Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * workaround * try mac https://stackoverflow.com/questions/23905661/on-mac-g-clang-fails-to-search-usr-local-include-and-usr-local-lib-by-def * Disable temp. arm64 docker image builds --------- Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
parent
8034ed3473
commit
128694213f
10 changed files with 1145 additions and 16 deletions
3
.github/workflows/bump_deps.yaml
vendored
3
.github/workflows/bump_deps.yaml
vendored
|
@ -12,6 +12,9 @@ jobs:
|
|||
- repository: "go-skynet/go-llama.cpp"
|
||||
variable: "GOLLAMA_VERSION"
|
||||
branch: "master"
|
||||
- repository: "ggerganov/llama.cpp"
|
||||
variable: "CPPLLAMA_VERSION"
|
||||
branch: "master"
|
||||
- repository: "go-skynet/go-ggml-transformers.cpp"
|
||||
variable: "GOGGMLTRANSFORMERS_VERSION"
|
||||
branch: "master"
|
||||
|
|
5
.github/workflows/image.yml
vendored
5
.github/workflows/image.yml
vendored
|
@ -19,7 +19,8 @@ jobs:
|
|||
matrix:
|
||||
include:
|
||||
- build-type: ''
|
||||
platforms: 'linux/amd64,linux/arm64'
|
||||
#platforms: 'linux/amd64,linux/arm64'
|
||||
platforms: 'linux/amd64'
|
||||
tag-latest: 'auto'
|
||||
tag-suffix: ''
|
||||
ffmpeg: ''
|
||||
|
@ -38,7 +39,7 @@ jobs:
|
|||
tag-suffix: '-cublas-cuda12'
|
||||
ffmpeg: ''
|
||||
- build-type: ''
|
||||
platforms: 'linux/amd64,linux/arm64'
|
||||
platforms: 'linux/amd64'
|
||||
tag-latest: 'false'
|
||||
tag-suffix: '-ffmpeg'
|
||||
ffmpeg: 'true'
|
||||
|
|
14
.github/workflows/release.yaml
vendored
14
.github/workflows/release.yaml
vendored
|
@ -29,6 +29,12 @@ jobs:
|
|||
run: |
|
||||
sudo apt-get update
|
||||
sudo apt-get install build-essential ffmpeg
|
||||
|
||||
git clone --recurse-submodules -b v1.58.0 --depth 1 --shallow-submodules https://github.com/grpc/grpc && \
|
||||
cd grpc && mkdir -p cmake/build && cd cmake/build && cmake -DgRPC_INSTALL=ON \
|
||||
-DgRPC_BUILD_TESTS=OFF \
|
||||
../.. && sudo make -j12 install
|
||||
|
||||
- name: Build
|
||||
id: build
|
||||
env:
|
||||
|
@ -66,12 +72,20 @@ jobs:
|
|||
- uses: actions/setup-go@v4
|
||||
with:
|
||||
go-version: '>=1.21.0'
|
||||
- name: Dependencies
|
||||
run: |
|
||||
git clone --recurse-submodules -b v1.58.0 --depth 1 --shallow-submodules https://github.com/grpc/grpc && \
|
||||
cd grpc && mkdir -p cmake/build && cd cmake/build && cmake -DgRPC_INSTALL=ON \
|
||||
-DgRPC_BUILD_TESTS=OFF \
|
||||
../.. && make -j12 install && rm -rf grpc
|
||||
- name: Build
|
||||
id: build
|
||||
env:
|
||||
CMAKE_ARGS: "${{ matrix.defines }}"
|
||||
BUILD_ID: "${{ matrix.build }}"
|
||||
run: |
|
||||
export C_INCLUDE_PATH=/usr/local/include
|
||||
export CPLUS_INCLUDE_PATH=/usr/local/include
|
||||
make dist
|
||||
- uses: actions/upload-artifact@v3
|
||||
with:
|
||||
|
|
20
.github/workflows/test.yml
vendored
20
.github/workflows/test.yml
vendored
|
@ -67,11 +67,15 @@ jobs:
|
|||
run: |
|
||||
sudo apt-get update
|
||||
sudo apt-get install build-essential ffmpeg
|
||||
|
||||
|
||||
sudo apt-get install -y ca-certificates cmake curl patch
|
||||
sudo apt-get install -y libopencv-dev && sudo ln -s /usr/include/opencv4/opencv2 /usr/include/opencv2
|
||||
sudo pip install -r extra/requirements.txt
|
||||
|
||||
|
||||
# Pre-build stable diffusion before we install a newever version of abseil (not compatible with stablediffusion-ncn)
|
||||
GO_TAGS="tts stablediffusion" GRPC_BACKENDS=backend-assets/grpc/stablediffusion make build
|
||||
|
||||
sudo mkdir /build && sudo chmod -R 777 /build && cd /build && \
|
||||
curl -L "https://github.com/gabime/spdlog/archive/refs/tags/v1.11.0.tar.gz" | \
|
||||
tar -xzvf - && \
|
||||
|
@ -87,6 +91,12 @@ jobs:
|
|||
sudo cp -rfv /build/lib/Linux-$(uname -m)/piper_phonemize/lib/. /usr/lib/ && \
|
||||
sudo ln -s /usr/lib/libpiper_phonemize.so /usr/lib/libpiper_phonemize.so.1 && \
|
||||
sudo cp -rfv /build/lib/Linux-$(uname -m)/piper_phonemize/include/. /usr/include/
|
||||
|
||||
git clone --recurse-submodules -b v1.58.0 --depth 1 --shallow-submodules https://github.com/grpc/grpc && \
|
||||
cd grpc && mkdir -p cmake/build && cd cmake/build && cmake -DgRPC_INSTALL=ON \
|
||||
-DgRPC_BUILD_TESTS=OFF \
|
||||
../.. && sudo make -j12 install
|
||||
|
||||
- name: Test
|
||||
run: |
|
||||
ESPEAK_DATA="/build/lib/Linux-$(uname -m)/piper_phonemize/lib/espeak-ng-data" GO_TAGS="tts stablediffusion" make test
|
||||
|
@ -108,6 +118,14 @@ jobs:
|
|||
# You can test your matrix by printing the current Go version
|
||||
- name: Display Go version
|
||||
run: go version
|
||||
- name: Dependencies
|
||||
run: |
|
||||
git clone --recurse-submodules -b v1.58.0 --depth 1 --shallow-submodules https://github.com/grpc/grpc && \
|
||||
cd grpc && mkdir -p cmake/build && cd cmake/build && cmake -DgRPC_INSTALL=ON \
|
||||
-DgRPC_BUILD_TESTS=OFF \
|
||||
../.. && make -j12 install && rm -rf grpc
|
||||
- name: Test
|
||||
run: |
|
||||
export C_INCLUDE_PATH=/usr/local/include
|
||||
export CPLUS_INCLUDE_PATH=/usr/local/include
|
||||
CMAKE_ARGS="-DLLAMA_F16C=OFF -DLLAMA_AVX512=OFF -DLLAMA_AVX2=OFF -DLLAMA_FMA=OFF" make test
|
Loading…
Add table
Add a link
Reference in a new issue