mirror of
https://github.com/ggerganov/llama.cpp.git
synced 2024-09-23 05:26:19 +00:00
9731134296
* server: tests: add models endpoint scenario * server: /v1/models add some metadata * server: tests: add debug field in context before scenario * server: tests: download model from HF, add batch size * server: tests: add passkey test * server: tests: add group attention params * server: do not truncate prompt tokens if self-extend through group attention is enabled * server: logs: do not truncate log values * server: tests - passkey - first good working value of nga * server: tests: fix server timeout * server: tests: fix passkey, add doc, fix regex content matching, fix timeout * server: tests: fix regex content matching * server: tests: schedule slow tests on master * server: metrics: fix when no prompt processed * server: tests: self-extend add llama-2-7B and Mixtral-8x7B-v0.1 * server: tests: increase timeout for completion * server: tests: keep only the PHI-2 test * server: tests: passkey add a negative test
87 lines
2.3 KiB
YAML
87 lines
2.3 KiB
YAML
# Server build and tests
|
|
name: Server
|
|
|
|
on:
|
|
workflow_dispatch: # allows manual triggering
|
|
push:
|
|
branches:
|
|
- master
|
|
paths: ['.github/workflows/server.yml', '**/CMakeLists.txt', '**/Makefile', '**/*.h', '**/*.hpp', '**/*.c', '**/*.cpp', '**/*.cu', '**/*.swift', '**/*.m', 'examples/server/tests/**.*']
|
|
pull_request:
|
|
types: [opened, synchronize, reopened]
|
|
paths: ['.github/workflows/server.yml', '**/CMakeLists.txt', '**/Makefile', '**/*.h', '**/*.hpp', '**/*.c', '**/*.cpp', '**/*.cu', '**/*.swift', '**/*.m', 'examples/server/tests/**.*']
|
|
schedule:
|
|
- cron: '00 0 * * *'
|
|
|
|
jobs:
|
|
server:
|
|
runs-on: ubuntu-latest
|
|
|
|
strategy:
|
|
matrix:
|
|
sanitizer: [ADDRESS, THREAD, UNDEFINED]
|
|
build_type: [Debug, Release]
|
|
include:
|
|
- build_type: Release
|
|
sanitizer: ""
|
|
exclude:
|
|
- build_type: Release
|
|
sanitizer: ADDRESS
|
|
- build_type: Release
|
|
sanitizer: THREAD
|
|
- build_type: Release
|
|
sanitizer: UNDEFINED
|
|
|
|
container:
|
|
image: ubuntu:latest
|
|
ports:
|
|
- 8888
|
|
options: --cpus 4
|
|
|
|
steps:
|
|
- name: Clone
|
|
id: checkout
|
|
uses: actions/checkout@v3
|
|
|
|
- name: Dependencies
|
|
id: depends
|
|
run: |
|
|
apt-get update
|
|
apt-get -y install \
|
|
build-essential \
|
|
git \
|
|
cmake \
|
|
python3-pip \
|
|
wget \
|
|
psmisc
|
|
|
|
- name: Build
|
|
id: cmake_build
|
|
run: |
|
|
mkdir build
|
|
cd build
|
|
cmake .. \
|
|
-DLLAMA_NATIVE=OFF \
|
|
-DLLAMA_BUILD_SERVER=ON \
|
|
-DCMAKE_BUILD_TYPE=${{ matrix.build_type }} \
|
|
-DLLAMA_SANITIZE_${{ matrix.sanitizer }}=ON ;
|
|
cmake --build . --config ${{ matrix.build_type }} -j $(nproc) --target server
|
|
|
|
- name: Tests dependencies
|
|
id: test_dependencies
|
|
run: |
|
|
pip install -r examples/server/tests/requirements.txt
|
|
|
|
- name: Tests
|
|
id: server_integration_tests
|
|
run: |
|
|
cd examples/server/tests
|
|
PORT=8888 ./tests.sh
|
|
|
|
- name: Slow tests
|
|
id: server_integration_tests_slow
|
|
if: github.event.schedule != ''
|
|
run: |
|
|
cd examples/server/tests
|
|
PORT=8888 ./tests.sh --stop --no-skipped --no-capture --tags slow
|