[unittest] add unit test to test quant args of srt engine #3225
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: | |
| inputs: | |
| version: | |
| description: "FlashInfer version" | |
| required: true | |
| type: choice | |
| default: 'release' | |
| options: | |
| - 'release' | |
| - 'nightly' | |
| 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 | |
| env: | |
| FLASHINFER_REPO: ${{ inputs.version == 'nightly' && 'https://flashinfer.ai/whl/nightly/cu121/torch2.4/flashinfer' || 'https://flashinfer.ai/whl/cu121/torch2.4/flashinfer' }} | |
| run: | | |
| bash scripts/ci_install_dependency.sh | |
| - name: Run test | |
| timeout-minutes: 10 | |
| run: | | |
| cd test/lang | |
| python3 run_suite.py --suite minimal | |
| unit-test-backend-1-gpu: | |
| if: github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request' | |
| runs-on: 1-gpu-runner | |
| strategy: | |
| matrix: | |
| range: [0-6, 6-15, 15-23, 23-30, 30-100] | |
| steps: | |
| - name: Checkout code | |
| uses: actions/checkout@v3 | |
| - name: Install dependencies | |
| env: | |
| FLASHINFER_REPO: ${{ inputs.version == 'nightly' && 'https://flashinfer.ai/whl/nightly/cu121/torch2.4/flashinfer' || 'https://flashinfer.ai/whl/cu121/torch2.4/flashinfer' }} | |
| run: | | |
| bash scripts/ci_install_dependency.sh | |
| - name: Run test | |
| timeout-minutes: 25 | |
| run: | | |
| cd test/srt | |
| RANGE=${{ matrix.range }} | |
| range_begin=${RANGE%-*} | |
| range_end=${RANGE#*-} | |
| python3 run_suite.py --suite minimal --range-begin ${range_begin} --range-end ${range_end} | |
| unit-test-backend-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 | |
| env: | |
| FLASHINFER_REPO: ${{ inputs.version == 'nightly' && 'https://flashinfer.ai/whl/nightly/cu121/torch2.4/flashinfer' || 'https://flashinfer.ai/whl/cu121/torch2.4/flashinfer' }} | |
| run: | | |
| bash scripts/ci_install_dependency.sh | |
| - name: Evaluate data parallelism accuracy (DP=2) | |
| timeout-minutes: 10 | |
| run: | | |
| cd test/srt | |
| python3 test_data_parallelism.py | |
| - name: Evaluate MLA accuracy (TP=2) | |
| timeout-minutes: 10 | |
| run: | | |
| cd test/srt | |
| python3 test_mla.py | |
| python3 test_mla_fp8.py | |
| python3 test_dp_attention.py | |
| - name: Test update weights from distributed | |
| timeout-minutes: 10 | |
| run: | | |
| cd test/srt | |
| python3 test_update_weights_from_distributed.py | |
| - name: Evaluate MoE EP accuracy (TP=2) | |
| timeout-minutes: 10 | |
| run: | | |
| cd test/srt | |
| python3 test_moe_ep.py | |
| performance-test-1-gpu-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 | |
| env: | |
| FLASHINFER_REPO: ${{ inputs.version == 'nightly' && 'https://flashinfer.ai/whl/nightly/cu121/torch2.4/flashinfer' || 'https://flashinfer.ai/whl/cu121/torch2.4/flashinfer' }} | |
| run: | | |
| bash scripts/ci_install_dependency.sh | |
| - name: Benchmark single latency | |
| timeout-minutes: 10 | |
| run: | | |
| cd test/srt | |
| python3 -m unittest test_bench_one_batch.TestBenchOneBatch.test_default | |
| - name: Benchmark online latency | |
| timeout-minutes: 10 | |
| run: | | |
| cd test/srt | |
| python3 -m unittest test_bench_serving.TestBenchServing.test_online_latency_default | |
| - name: Benchmark offline throughput | |
| timeout-minutes: 10 | |
| run: | | |
| cd test/srt | |
| python3 -m unittest test_bench_serving.TestBenchServing.test_offline_throughput_default | |
| - name: Benchmark offline throughput (Non-streaming, small batch size) | |
| timeout-minutes: 10 | |
| run: | | |
| cd test/srt | |
| python3 -m unittest test_bench_serving.TestBenchServing.test_offline_throughput_non_stream_small_batch_size | |
| performance-test-1-gpu-part-2: | |
| 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 | |
| env: | |
| FLASHINFER_REPO: ${{ inputs.version == 'nightly' && 'https://flashinfer.ai/whl/nightly/cu121/torch2.4/flashinfer' || 'https://flashinfer.ai/whl/cu121/torch2.4/flashinfer' }} | |
| run: | | |
| bash scripts/ci_install_dependency.sh | |
| - name: Benchmark offline throughput (w/o RadixAttention) | |
| timeout-minutes: 10 | |
| run: | | |
| cd test/srt | |
| python3 -m unittest test_bench_serving.TestBenchServing.test_offline_throughput_without_radix_cache | |
| - name: Benchmark offline throughput (w/ Triton) | |
| timeout-minutes: 10 | |
| run: | | |
| cd test/srt | |
| python3 -m unittest test_bench_serving.TestBenchServing.test_offline_throughput_with_triton_attention_backend | |
| - name: Benchmark offline throughput (w/ FP8) | |
| timeout-minutes: 10 | |
| run: | | |
| cd test/srt | |
| python3 -m unittest test_bench_serving.TestBenchServing.test_offline_throughput_default_fp8 | |
| 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 | |
| env: | |
| FLASHINFER_REPO: ${{ inputs.version == 'nightly' && 'https://flashinfer.ai/whl/nightly/cu121/torch2.4/flashinfer' || 'https://flashinfer.ai/whl/cu121/torch2.4/flashinfer' }} | |
| run: | | |
| bash scripts/ci_install_dependency.sh | |
| - name: Benchmark single latency (TP=2) | |
| timeout-minutes: 10 | |
| run: | | |
| cd test/srt | |
| python3 -m unittest test_bench_one_batch.TestBenchOneBatch.test_moe_default | |
| - name: Benchmark offline throughput (TP=2) | |
| timeout-minutes: 10 | |
| run: | | |
| cd test/srt | |
| python3 -m unittest test_bench_serving.TestBenchServing.test_moe_offline_throughput_default | |
| - name: Benchmark offline throughput (w/o RadixAttention) (TP=2) | |
| timeout-minutes: 10 | |
| run: | | |
| cd test/srt | |
| python3 -m unittest test_bench_serving.TestBenchServing.test_moe_offline_throughput_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 | |
| env: | |
| FLASHINFER_REPO: ${{ inputs.version == 'nightly' && 'https://flashinfer.ai/whl/nightly/cu121/torch2.4/flashinfer' || 'https://flashinfer.ai/whl/cu121/torch2.4/flashinfer' }} | |
| run: | | |
| bash scripts/ci_install_dependency.sh | |
| 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 | |
| env: | |
| FLASHINFER_REPO: ${{ inputs.version == 'nightly' && 'https://flashinfer.ai/whl/nightly/cu121/torch2.4/flashinfer' || 'https://flashinfer.ai/whl/cu121/torch2.4/flashinfer' }} | |
| run: | | |
| bash scripts/ci_install_dependency.sh | |
| git clone https://github.com/merrymercy/human-eval.git | |
| cd human-eval | |
| pip install -e . | |
| - name: Evaluate accuracy (TP=2) | |
| timeout-minutes: 20 | |
| run: | | |
| cd test/srt | |
| python3 test_moe_eval_accuracy_large.py | |
| finish: | |
| needs: [ | |
| unit-test-frontend, unit-test-backend-1-gpu, unit-test-backend-2-gpu, | |
| performance-test-1-gpu-part-1, performance-test-1-gpu-part-2, 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." |