server: bench: create a script to wrap all operations #52
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
# Benchmark | |
name: Benchmark | |
on: | |
workflow_dispatch: | |
inputs: | |
gpu-series: | |
description: 'Azure GPU series to run with' | |
required: true | |
type: choice | |
options: | |
- Standard_NC4as_T4_v3 | |
- Standard_NC64as_T4_v3 | |
- Standard_NC24ads_A100_v4 | |
- Standard_NC48ads_A100_v4 | |
- Standard_ND96asr_A100_v4 | |
- Standard_NC40ads_H100_v5 | |
- Standard_NC80adis_H100_v5 | |
push: | |
branches: | |
- master | |
- hp/server/bench/workflow # FIXME remove | |
paths: ['.github/workflows/server.yml', '**/CMakeLists.txt', '**/Makefile', '**/*.h', '**/*.hpp', '**/*.c', '**/*.cpp', '**/*.cu', '**/*.swift', '**/*.m', 'examples/server/bench/**.*'] | |
pull_request: | |
types: [opened, synchronize, reopened] | |
paths: ['.github/workflows/server.yml', '**/CMakeLists.txt', '**/Makefile', '**/*.h', '**/*.hpp', '**/*.c', '**/*.cpp', '**/*.cu', '**/*.swift', '**/*.m', 'examples/server/bench/**.*'] | |
schedule: | |
- cron: '04 2 * * *' | |
concurrency: | |
group: ${{ github.workflow }}-${{ github.ref }} | |
cancel-in-progress: true | |
jobs: | |
bench-server-baseline: | |
runs-on: Standard_NC4as_T4_v3 | |
if: ${{ github.event.schedule || github.event.inputs.gpu-series == 'Standard_NC4as_T4_v3' || github.event.pull_request || github.event.push.ref == 'refs/heads/master' }} | |
steps: | |
- name: Clone | |
id: checkout | |
uses: actions/checkout@v3 | |
with: | |
fetch-depth: 0 | |
- name: Install python env | |
id: pipenv | |
run: | | |
cd examples/server/bench | |
python -m venv venv | |
source venv/bin/activate | |
pip install -r requirements.txt | |
- name: Prometheus | |
id: install_prometheus | |
run: | | |
wget --quiet https://github.com/prometheus/prometheus/releases/download/v2.51.0/prometheus-2.51.0.linux-amd64.tar.gz | |
tar xzf prometheus*.tar.gz --strip-components=1 | |
./prometheus --config.file=examples/server/bench/prometheus.yml & | |
while ! nc -z localhost 9090; do | |
sleep 0.1 | |
done | |
- name: Build | |
id: cmake_build | |
run: | | |
set -eux | |
mkdir build | |
cd build | |
cmake .. \ | |
-DLLAMA_NATIVE=OFF \ | |
-DLLAMA_BUILD_SERVER=ON \ | |
-DLLAMA_CURL=ON \ | |
-DLLAMA_CUBLAS=ON \ | |
-DCUDAToolkit_ROOT=/usr/local/cuda \ | |
-DCMAKE_CUDA_COMPILER=/usr/local/cuda/bin/nvcc \ | |
-DCMAKE_CUDA_ARCHITECTURES=75 \ | |
-DLLAMA_FATAL_WARNINGS=OFF \ | |
-DLLAMA_ALL_WARNINGS=OFF \ | |
-DCMAKE_BUILD_TYPE=Release; | |
cmake --build . --config Release -j $(nproc) --target server | |
- name: Install k6 | |
id: k6_installation | |
run: | | |
wget --quiet https://github.com/grafana/k6/releases/download/v0.49.0/k6-v0.49.0-linux-amd64.tar.gz | |
tar xzf k6*.tar.gz --strip-components=1 | |
- name: Download the dataset | |
id: download_dataset | |
run: | | |
cd examples/server/bench | |
wget --quiet https://huggingface.co/datasets/anon8231489123/ShareGPT_Vicuna_unfiltered/resolve/main/ShareGPT_V3_unfiltered_cleaned_split.json | |
- name: Server bench | |
id: server_bench | |
run: | | |
set -eux | |
cd examples/server/bench | |
BENCH_K6_BIN_PATH=./k6 python bench.py \ | |
--runner-label Standard_NC4as_T4_v3 \ | |
--scenario script.js \ | |
--duration 5m \ | |
--hf-repo ggml-org/models \ | |
--hf-file phi-2/ggml-model-q4_0.gguf \ | |
--model-path-prefix /models/phi-2/ggml-model-q4_0.gguf \ | |
--parallel 8 \ | |
-ngl 33 \ | |
--batch-size 2048 \ | |
--ubatch-size 256 \ | |
--ctx-size 16384 \ | |
--n-prompts 1000 \ | |
--max-prompt-tokens 1024 \ | |
--max-tokens 2048 | |
cat results.github.env >> $GITHUB_ENV | |
- name: Comment PR | |
uses: thollander/actions-comment-pull-request@v2 | |
with: | |
message: | | |
Request duration: ${HTTP_REQ_DURATION_AVG} |