server : fix token duplication when streaming with stop strings #9389
Workflow file for this run
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# Server build and tests | |
name: Server | |
on: | |
workflow_dispatch: # allows manual triggering | |
inputs: | |
sha: | |
description: 'Commit SHA1 to build' | |
required: false | |
type: string | |
slow_tests: | |
description: 'Run slow tests' | |
required: true | |
type: boolean | |
push: | |
branches: | |
- master | |
paths: ['.github/workflows/server.yml', '**/CMakeLists.txt', '**/Makefile', '**/*.h', '**/*.hpp', '**/*.c', '**/*.cpp', '**/*.cu', '**/*.swift', '**/*.m', 'examples/server/**.*'] | |
pull_request: | |
types: [opened, synchronize, reopened] | |
paths: ['.github/workflows/server.yml', '**/CMakeLists.txt', '**/Makefile', '**/*.h', '**/*.hpp', '**/*.c', '**/*.cpp', '**/*.cu', '**/*.swift', '**/*.m', 'examples/server/**.*'] | |
env: | |
LLAMA_LOG_COLORS: 1 | |
LLAMA_LOG_PREFIX: 1 | |
LLAMA_LOG_TIMESTAMPS: 1 | |
LLAMA_LOG_VERBOSITY: 10 | |
concurrency: | |
group: ${{ github.workflow }}-${{ github.ref }}-${{ github.head_ref || github.run_id }} | |
cancel-in-progress: true | |
jobs: | |
server: | |
runs-on: ubuntu-latest | |
strategy: | |
matrix: | |
sanitizer: [ADDRESS, UNDEFINED] # THREAD is broken | |
build_type: [RelWithDebInfo] | |
include: | |
- build_type: Release | |
sanitizer: "" | |
fail-fast: false # While -DLLAMA_SANITIZE_THREAD=ON is broken | |
steps: | |
- name: Dependencies | |
id: depends | |
run: | | |
sudo apt-get update | |
sudo apt-get -y install \ | |
build-essential \ | |
xxd \ | |
git \ | |
cmake \ | |
curl \ | |
wget \ | |
language-pack-en \ | |
libcurl4-openssl-dev | |
- name: Clone | |
id: checkout | |
uses: actions/checkout@v4 | |
with: | |
fetch-depth: 0 | |
ref: ${{ github.event.inputs.sha || github.event.pull_request.head.sha || github.sha || github.head_ref || github.ref_name }} | |
- name: Python setup | |
id: setup_python | |
uses: actions/setup-python@v5 | |
with: | |
python-version: '3.11' | |
- name: Tests dependencies | |
id: test_dependencies | |
run: | | |
pip install -r examples/server/tests/requirements.txt | |
# Setup nodejs (to be used for verifying bundled index.html) | |
- uses: actions/setup-node@v4 | |
with: | |
node-version: '22.11.0' | |
- name: Verify bundled index.html | |
id: verify_server_index_html | |
run: | | |
git config --global --add safe.directory $(realpath .) | |
cd examples/server/webui | |
git status | |
npm ci | |
npm run build | |
git status | |
modified_files="$(git status -s)" | |
echo "Modified files: ${modified_files}" | |
if [ -n "${modified_files}" ]; then | |
echo "Repository is dirty or server/webui is not built as expected" | |
echo "Hint: You may need to follow Web UI build guide in server/README.md" | |
echo "${modified_files}" | |
exit 1 | |
fi | |
- name: Build (no OpenMP) | |
id: cmake_build_no_openmp | |
if: ${{ matrix.sanitizer == 'THREAD' }} | |
run: | | |
cmake -B build \ | |
-DGGML_NATIVE=OFF \ | |
-DLLAMA_BUILD_SERVER=ON \ | |
-DLLAMA_CURL=ON \ | |
-DCMAKE_BUILD_TYPE=${{ matrix.build_type }} \ | |
-DLLAMA_SANITIZE_${{ matrix.sanitizer }}=ON \ | |
-DGGML_OPENMP=OFF ; | |
cmake --build build --config ${{ matrix.build_type }} -j $(nproc) --target llama-server | |
- name: Build | |
id: cmake_build | |
if: ${{ matrix.sanitizer != 'THREAD' }} | |
run: | | |
cmake -B build \ | |
-DGGML_NATIVE=OFF \ | |
-DLLAMA_BUILD_SERVER=ON \ | |
-DLLAMA_CURL=ON \ | |
-DCMAKE_BUILD_TYPE=${{ matrix.build_type }} \ | |
-DLLAMA_SANITIZE_${{ matrix.sanitizer }}=ON ; | |
cmake --build build --config ${{ matrix.build_type }} -j $(nproc) --target llama-server | |
- name: Tests | |
id: server_integration_tests | |
run: | | |
cd examples/server/tests | |
./tests.sh | |
- name: Slow tests | |
id: server_integration_tests_slow | |
if: ${{ (github.event.schedule || github.event.inputs.slow_tests == 'true') && matrix.build_type == 'Release' }} | |
run: | | |
cd examples/server/tests | |
SLOW_TESTS=1 ./tests.sh | |
server-windows: | |
runs-on: windows-2019 | |
steps: | |
- name: Clone | |
id: checkout | |
uses: actions/checkout@v4 | |
with: | |
fetch-depth: 0 | |
ref: ${{ github.event.inputs.sha || github.event.pull_request.head.sha || github.sha || github.head_ref || github.ref_name }} | |
- name: libCURL | |
id: get_libcurl | |
env: | |
CURL_VERSION: 8.6.0_6 | |
run: | | |
curl.exe -o $env:RUNNER_TEMP/curl.zip -L "https://curl.se/windows/dl-${env:CURL_VERSION}/curl-${env:CURL_VERSION}-win64-mingw.zip" | |
mkdir $env:RUNNER_TEMP/libcurl | |
tar.exe -xvf $env:RUNNER_TEMP/curl.zip --strip-components=1 -C $env:RUNNER_TEMP/libcurl | |
- name: Build | |
id: cmake_build | |
run: | | |
cmake -B build -DLLAMA_CURL=ON -DCURL_LIBRARY="$env:RUNNER_TEMP/libcurl/lib/libcurl.dll.a" -DCURL_INCLUDE_DIR="$env:RUNNER_TEMP/libcurl/include" | |
cmake --build build --config Release -j ${env:NUMBER_OF_PROCESSORS} --target llama-server | |
- name: Python setup | |
id: setup_python | |
uses: actions/setup-python@v5 | |
with: | |
python-version: '3.11' | |
- name: Tests dependencies | |
id: test_dependencies | |
run: | | |
pip install -r examples/server/tests/requirements.txt | |
- name: Copy Libcurl | |
id: prepare_libcurl | |
run: | | |
cp $env:RUNNER_TEMP/libcurl/bin/libcurl-x64.dll ./build/bin/Release/libcurl-x64.dll | |
- name: Tests | |
id: server_integration_tests | |
if: ${{ !matrix.disabled_on_pr || !github.event.pull_request }} | |
run: | | |
cd examples/server/tests | |
$env:PYTHONIOENCODING = ":replace" | |
pytest -v -x | |
- name: Slow tests | |
id: server_integration_tests_slow | |
if: ${{ (github.event.schedule || github.event.inputs.slow_tests == 'true') && matrix.build_type == 'Release' }} | |
run: | | |
cd examples/server/tests | |
$env:SLOW_TESTS = "1" | |
pytest -v -x |