78 lines
2.4 KiB
YAML
78 lines
2.4 KiB
YAML
name: PR E2E Test
|
|
|
|
on:
|
|
push:
|
|
branches: [ main ]
|
|
paths:
|
|
- "python/sglang/*"
|
|
- "python/sglang/lang/*"
|
|
- "python/sglang/lang/backend/*"
|
|
- "python/sglang/srt/*"
|
|
- "python/sglang/srt/constrained/*"
|
|
- "python/sglang/srt/layers/*"
|
|
- "python/sglang/srt/layers/quantization/*"
|
|
- "python/sglang/srt/managers/*"
|
|
- "python/sglang/srt/mem_cache/*"
|
|
- "python/sglang/srt/model_executor/*"
|
|
- "python/sglang/srt/model_loader/*"
|
|
- "python/sglang/srt/models/*"
|
|
- "python/sglang/srt/openai_api/*"
|
|
- "python/sglang/test/*"
|
|
pull_request:
|
|
branches: [ main ]
|
|
paths:
|
|
- "python/sglang/*"
|
|
- "python/sglang/lang/*"
|
|
- "python/sglang/lang/backend/*"
|
|
- "python/sglang/srt/*"
|
|
- "python/sglang/srt/constrained/*"
|
|
- "python/sglang/srt/layers/*"
|
|
- "python/sglang/srt/layers/quantization/*"
|
|
- "python/sglang/srt/managers/*"
|
|
- "python/sglang/srt/mem_cache/*"
|
|
- "python/sglang/srt/model_executor/*"
|
|
- "python/sglang/srt/model_loader/*"
|
|
- "python/sglang/srt/models/*"
|
|
- "python/sglang/srt/openai_api/*"
|
|
- "python/sglang/test/*"
|
|
workflow_dispatch:
|
|
|
|
jobs:
|
|
gpu-job:
|
|
runs-on: self-hosted
|
|
env:
|
|
CUDA_VISIBLE_DEVICES: 6
|
|
|
|
steps:
|
|
- name: Checkout code
|
|
uses: actions/checkout@v3
|
|
|
|
- name: Install dependencies
|
|
run: |
|
|
pip install --upgrade pip
|
|
pip install -e "python[all]"
|
|
pip install flashinfer -i https://flashinfer.ai/whl/cu121/torch2.3/ --force-reinstall
|
|
pip install --upgrade transformers
|
|
|
|
- name: Launch server and run benchmark
|
|
run: |
|
|
python3 -m sglang.launch_server --model /home/lmzheng/zhyncs/Meta-Llama-3.1-8B-Instruct --port 8413 --disable-radix-cache &
|
|
|
|
echo "Waiting for server to start..."
|
|
for i in {1..120}; do
|
|
if curl -s http://127.0.0.1:8413/health; then
|
|
echo "Server is up!"
|
|
break
|
|
fi
|
|
if [ $i -eq 120 ]; then
|
|
echo "Server failed to start within 120 seconds"
|
|
exit 1
|
|
fi
|
|
sleep 1
|
|
done
|
|
|
|
cd /home/lmzheng/zhyncs && python3 -m sglang.bench_serving --backend sglang --port 8413 --dataset-name random --num-prompts 3000 --random-input 256 --random-output 512
|
|
|
|
echo "Stopping server..."
|
|
kill -9 $(ps aux | grep sglang | grep Meta-Llama-3.1-8B-Instruct | grep -v grep | awk '{print $2}')
|