Resources aware load balance method #6
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
| name: PR Test | |
| on: | |
| push: | |
| branches: [ main ] | |
| paths: | |
| - "python/sglang/**" | |
| - "test/**" | |
| pull_request: | |
| branches: [ main ] | |
| paths: | |
| - "python/sglang/**" | |
| - "test/**" | |
| workflow_dispatch: | |
| concurrency: | |
| group: pr-test-${{ github.ref }} | |
| cancel-in-progress: true | |
| jobs: | |
| unit-test-frontend: | |
| if: github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request' | |
| runs-on: 1-gpu-runner | |
| steps: | |
| - name: Checkout code | |
| uses: actions/checkout@v3 | |
| - name: Install dependencies | |
| run: | | |
| pip install --upgrade pip | |
| pip install -e "python[dev]" | |
| pip install flashinfer -i https://flashinfer.ai/whl/cu121/torch2.4/ --force-reinstall | |
| - name: Run test | |
| timeout-minutes: 20 | |
| run: | | |
| cd test/lang | |
| python3 run_suite.py --suite minimal | |
| unit-test-backend-part-0: | |
| if: github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request' | |
| runs-on: 1-gpu-runner | |
| steps: | |
| - name: Checkout code | |
| uses: actions/checkout@v3 | |
| - name: Install dependencies | |
| run: | | |
| pip install --upgrade pip | |
| pip install -e "python[dev]" | |
| pip install flashinfer -i https://flashinfer.ai/whl/cu121/torch2.4/ --force-reinstall | |
| - name: Run test | |
| timeout-minutes: 20 | |
| run: | | |
| cd test/srt | |
| python3 run_suite.py --suite minimal --range-begin 0 --range-end 8 | |
| unit-test-backend-part-1: | |
| if: github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request' | |
| runs-on: 1-gpu-runner | |
| steps: | |
| - name: Checkout code | |
| uses: actions/checkout@v3 | |
| - name: Install dependencies | |
| run: | | |
| pip install --upgrade pip | |
| pip install -e "python[dev]" | |
| pip install flashinfer -i https://flashinfer.ai/whl/cu121/torch2.4/ --force-reinstall | |
| - name: Run test | |
| timeout-minutes: 20 | |
| run: | | |
| cd test/srt | |
| python3 run_suite.py --suite minimal --range-begin 8 | |
| performance-test-1-gpu: | |
| if: github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request' | |
| runs-on: 1-gpu-runner | |
| 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/torch2.4/ --force-reinstall | |
| - name: Benchmark Serving Throughput | |
| timeout-minutes: 10 | |
| run: | | |
| cd test/srt | |
| python3 -m unittest test_serving_throughput.TestServingThroughput.test_default | |
| - name: Benchmark Serving Latency | |
| timeout-minutes: 10 | |
| run: | | |
| cd test/srt | |
| python3 -m unittest test_serving_latency.TestServingLatency.test_default | |
| - name: Benchmark Serving Throughput (w/o RadixAttention) | |
| timeout-minutes: 10 | |
| run: | | |
| cd test/srt | |
| python3 -m unittest test_serving_throughput.TestServingThroughput.test_default_without_radix_cache | |
| - name: Benchmark Serving Throughput (w/o ChunkedPrefill) | |
| timeout-minutes: 10 | |
| run: | | |
| cd test/srt | |
| python3 -m unittest test_serving_throughput.TestServingThroughput.test_default_without_chunked_prefill | |
| performance-test-2-gpu: | |
| if: github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request' | |
| runs-on: 2-gpu-runner | |
| 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/torch2.4/ --force-reinstall | |
| - name: Benchmark Serving Throughput (TP=2) | |
| timeout-minutes: 10 | |
| run: | | |
| cd test/srt | |
| python3 -m unittest test_moe_serving_throughput.TestServingThroughput.test_default | |
| - name: Benchmark Serving Latency (TP=2) | |
| timeout-minutes: 10 | |
| run: | | |
| cd test/srt | |
| python3 -m unittest test_moe_serving_latency.TestServingLatency.test_default | |
| - name: Benchmark Serving Throughput (w/o RadixAttention) (TP=2) | |
| timeout-minutes: 10 | |
| run: | | |
| cd test/srt | |
| python3 -m unittest test_moe_serving_throughput.TestServingThroughput.test_default_without_radix_cache | |
| accuracy-test-1-gpu: | |
| if: github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request' | |
| runs-on: 1-gpu-runner | |
| 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/torch2.4/ --force-reinstall | |
| git clone https://github.com/merrymercy/human-eval.git | |
| cd human-eval | |
| pip install -e . | |
| - name: Evaluate Accuracy | |
| timeout-minutes: 20 | |
| run: | | |
| cd test/srt | |
| python3 test_eval_accuracy_large.py | |
| accuracy-test-2-gpu: | |
| if: github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request' | |
| runs-on: 2-gpu-runner | |
| 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/torch2.4/ --force-reinstall | |
| git clone https://github.com/merrymercy/human-eval.git | |
| cd human-eval | |
| pip install -e . | |
| - name: Evaluate Accuracy | |
| timeout-minutes: 20 | |
| run: | | |
| cd test/srt | |
| python3 test_moe_eval_accuracy_large.py | |
| finish: | |
| needs: [ | |
| unit-test-frontend, unit-test-backend-part-0, unit-test-backend-part-1, | |
| performance-test-1-gpu, performance-test-2-gpu, | |
| accuracy-test-1-gpu, accuracy-test-2-gpu | |
| ] | |
| runs-on: ubuntu-latest | |
| steps: | |
| - name: Finish | |
| run: echo "This is an empty step to ensure that all jobs are completed." |