Skip to content
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

41 feat batch inference for nitro #101

Merged
merged 6 commits into from
Nov 6, 2023
Merged

41 feat batch inference for nitro #101

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
26daebc
chore: pump llama cpp to latest version with batch inference
tikikun Oct 26, 2023
2212f89
pump llama
tikikun Nov 3, 2023
d89f30c
feat: add batching inferences + multi threading in drogon cpp
tikikun Nov 3, 2023
f9d03a5
remove specific mac
tikikun Nov 6, 2023
b953692
disable DBUILD_SHARED_LIBS cmake windows cuda
jan-service-account Nov 6, 2023
a463cdb
Merge pull request #108 from janhq/fix/missing-dll-libs
hiento09 Nov 6, 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
6 changes: 1 addition & 5 deletions .github/workflows/build.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -276,8 +276,6 @@ jobs:
run: |
robocopy build_deps\_install\bin .\build\Release zlib.dll
robocopy build\bin\Release .\build\Release llama.dll
robocopy ext_libs .\build\Release libcrypto-3-x64.dll
robocopy ext_libs .\build\Release libssl-3-x64.dll
7z a nitro.zip .\build\Release\*

- uses: actions/[email protected]
Expand Down Expand Up @@ -325,7 +323,7 @@ jobs:
cmake --build ./build_deps/nitro_deps --config Release
mkdir -p build
cd build
cmake .. -DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_CUBLAS=ON -DBUILD_SHARED_LIBS=ON
cmake .. -DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_CUBLAS=ON
cmake --build . --config Release -j 4

- name: Pack artifacts
Expand All @@ -336,8 +334,6 @@ jobs:
echo %PATH%
robocopy build_deps\_install\bin .\build\Release zlib.dll
robocopy build\bin\Release .\build\Release llama.dll
robocopy ext_libs .\build\Release libcrypto-3-x64.dll
robocopy ext_libs .\build\Release libssl-3-x64.dll
7z a nitro.zip .\build\Release\*

- uses: actions/[email protected]
Expand Down
5 changes: 4 additions & 1 deletion CMakeLists.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -16,6 +16,9 @@ else()
set(CMAKE_CXX_STANDARD 14)
endif()

# llama cpp server need llava example to work, this is for llama cpp server
set(LLAMA_BUILD_EXAMPLES ON)

set(CMAKE_CXX_STANDARD_REQUIRED ON)
set(CMAKE_CXX_EXTENSIONS OFF)
set(OPENSSL_USE_STATIC_LIBS TRUE)
Expand Down Expand Up @@ -48,7 +51,7 @@ add_executable(${PROJECT_NAME} main.cc)
#
# and comment out the following lines
find_package(Drogon CONFIG REQUIRED)
target_link_libraries(${PROJECT_NAME} PRIVATE Drogon::Drogon common llama
target_link_libraries(${PROJECT_NAME} PRIVATE Drogon::Drogon common llama clip
${CMAKE_THREAD_LIBS_INIT})

# ##############################################################################
Expand Down
Loading
Loading