EngineX-Hygon/sglang
5
0
Fork 0
Code Issues Pull Requests Actions 7 Projects Releases Wiki Activity

Reorganize CI and test files (#9027)

Browse Source
This commit is contained in:
Lianmin Zheng
2025-08-10 12:30:06 -07:00
committed by GitHub
parent b58ae7a2a0
commit 2c7f01bc89
66 changed files with 161 additions and 195 deletions
Download Patch File Download Diff File Expand all files Collapse all files

84
.github/workflows/pr-test-amd.yml vendored
View File

@@ -36,19 +36,19 @@ jobs:
uses: actions/checkout@v4
- name: Start CI container
run: bash scripts/amd_ci_start_container.sh
run: bash scripts/ci/amd_ci_start_container.sh
env:
GITHUB_WORKSPACE: ${{ github.workspace }}
- name: Install dependencies
run: bash scripts/amd_ci_install_dependency.sh
run: bash scripts/ci/amd_ci_install_dependency.sh
- name: Evaluate Accuracy
timeout-minutes: 30
run: |
bash scripts/amd_ci_exec.sh -e SGLANG_USE_AITER=0 python3 test_eval_accuracy_large.py
bash scripts/amd_ci_exec.sh python3 test_eval_fp8_accuracy.py
bash scripts/amd_ci_exec.sh python3 models/test_qwen_models.py
bash scripts/ci/amd_ci_exec.sh -e SGLANG_USE_AITER=0 python3 test_eval_accuracy_large.py
bash scripts/ci/amd_ci_exec.sh python3 test_eval_fp8_accuracy.py
bash scripts/ci/amd_ci_exec.sh python3 models/test_qwen_models.py
accuracy-test-2-gpu-amd:
if: (github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request') &&
@@ -62,17 +62,17 @@ jobs:
uses: actions/checkout@v4
- name: Start CI container
run: bash scripts/amd_ci_start_container.sh
run: bash scripts/ci/amd_ci_start_container.sh
env:
GITHUB_WORKSPACE: ${{ github.workspace }}
- name: Install dependencies
run: bash scripts/amd_ci_install_dependency.sh
run: bash scripts/ci/amd_ci_install_dependency.sh
- name: Evaluate accuracy (TP=2)
timeout-minutes: 30
run: |
bash scripts/amd_ci_exec.sh -e SGLANG_USE_AITER=0 python3 test_moe_eval_accuracy_large.py
bash scripts/ci/amd_ci_exec.sh -e SGLANG_USE_AITER=0 python3 test_moe_eval_accuracy_large.py
mla-test-1-gpu-amd:
if: (github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request') &&
@@ -86,17 +86,17 @@ jobs:
uses: actions/checkout@v4
- name: Start CI container
run: bash scripts/amd_ci_start_container.sh
run: bash scripts/ci/amd_ci_start_container.sh
env:
GITHUB_WORKSPACE: ${{ github.workspace }}
- name: Install dependencies
run: bash scripts/amd_ci_install_dependency.sh
run: bash scripts/ci/amd_ci_install_dependency.sh
- name: MLA TEST
timeout-minutes: 30
run: |
bash scripts/amd_ci_exec.sh python3 test_mla.py
bash scripts/ci/amd_ci_exec.sh python3 test_mla.py
performance-test-1-gpu-part-1-amd:
if: (github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request') &&
@@ -110,33 +110,33 @@ jobs:
uses: actions/checkout@v4
- name: Start CI container
run: bash scripts/amd_ci_start_container.sh
run: bash scripts/ci/amd_ci_start_container.sh
env:
GITHUB_WORKSPACE: ${{ github.workspace }}
- name: Install dependencies
run: bash scripts/amd_ci_install_dependency.sh
run: bash scripts/ci/amd_ci_install_dependency.sh
- name: Benchmark single latency
timeout-minutes: 20
run: |
bash scripts/amd_ci_exec.sh python3 -m unittest test_bench_one_batch.TestBenchOneBatch.test_bs1_small
bash scripts/amd_ci_exec.sh python3 -m unittest test_bench_one_batch.TestBenchOneBatch.test_bs1_default
bash scripts/ci/amd_ci_exec.sh python3 -m unittest test_bench_one_batch.TestBenchOneBatch.test_bs1_small
bash scripts/ci/amd_ci_exec.sh python3 -m unittest test_bench_one_batch.TestBenchOneBatch.test_bs1_default
- name: Benchmark online latency
timeout-minutes: 15
run: |
bash scripts/amd_ci_exec.sh python3 -m unittest test_bench_serving.TestBenchServing.test_online_latency_default
bash scripts/ci/amd_ci_exec.sh python3 -m unittest test_bench_serving.TestBenchServing.test_online_latency_default
- name: Benchmark offline throughput
timeout-minutes: 15
run: |
bash scripts/amd_ci_exec.sh python3 -m unittest test_bench_serving.TestBenchServing.test_offline_throughput_default
bash scripts/ci/amd_ci_exec.sh python3 -m unittest test_bench_serving.TestBenchServing.test_offline_throughput_default
- name: Benchmark offline throughput (Non-streaming, small batch size)
timeout-minutes: 15
run: |
bash scripts/amd_ci_exec.sh python3 -m unittest test_bench_serving.TestBenchServing.test_offline_throughput_non_stream_small_batch_size
bash scripts/ci/amd_ci_exec.sh python3 -m unittest test_bench_serving.TestBenchServing.test_offline_throughput_non_stream_small_batch_size
performance-test-1-gpu-part-2-amd:
if: (github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request') &&
@@ -150,27 +150,27 @@ jobs:
uses: actions/checkout@v4
- name: Start CI container
run: bash scripts/amd_ci_start_container.sh
run: bash scripts/ci/amd_ci_start_container.sh
env:
GITHUB_WORKSPACE: ${{ github.workspace }}
- name: Install dependencies
run: bash scripts/amd_ci_install_dependency.sh
run: bash scripts/ci/amd_ci_install_dependency.sh
- name: Benchmark offline throughput (w/o RadixAttention)
timeout-minutes: 15
run: |
bash scripts/amd_ci_exec.sh python3 -m unittest test_bench_serving.TestBenchServing.test_offline_throughput_without_radix_cache
bash scripts/ci/amd_ci_exec.sh python3 -m unittest test_bench_serving.TestBenchServing.test_offline_throughput_without_radix_cache
- name: Benchmark offline throughput (w/ Triton)
timeout-minutes: 15
run: |
bash scripts/amd_ci_exec.sh python3 -m unittest test_bench_serving.TestBenchServing.test_offline_throughput_with_triton_attention_backend
bash scripts/ci/amd_ci_exec.sh python3 -m unittest test_bench_serving.TestBenchServing.test_offline_throughput_with_triton_attention_backend
- name: Benchmark offline throughput (w/ FP8)
timeout-minutes: 15
run: |
bash scripts/amd_ci_exec.sh python3 -m unittest test_bench_serving.TestBenchServing.test_offline_throughput_default_fp8
bash scripts/ci/amd_ci_exec.sh python3 -m unittest test_bench_serving.TestBenchServing.test_offline_throughput_default_fp8
bench-test-2-gpu-amd:
if: (github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request') &&
@@ -184,37 +184,37 @@ jobs:
uses: actions/checkout@v4
- name: Start CI container
run: bash scripts/amd_ci_start_container.sh
run: bash scripts/ci/amd_ci_start_container.sh
env:
GITHUB_WORKSPACE: ${{ github.workspace }}
- name: Install dependencies
run: bash scripts/amd_ci_install_dependency.sh
run: bash scripts/ci/amd_ci_install_dependency.sh
- name: Benchmark dummy grok (TP=2)
timeout-minutes: 30
run: |
bash scripts/amd_ci_exec.sh python3 models/test_dummy_grok_models.py
bash scripts/ci/amd_ci_exec.sh python3 models/test_dummy_grok_models.py
- name: Benchmark single latency (TP=2)
timeout-minutes: 25
run: |
bash scripts/amd_ci_exec.sh python3 -m unittest test_bench_one_batch.TestBenchOneBatch.test_moe_tp2_bs1
bash scripts/ci/amd_ci_exec.sh python3 -m unittest test_bench_one_batch.TestBenchOneBatch.test_moe_tp2_bs1
- name: Benchmark single latency + torch.compile (TP=2)
timeout-minutes: 25
run: |
bash scripts/amd_ci_exec.sh python3 -m unittest test_bench_one_batch.TestBenchOneBatch.test_torch_compile_tp2_bs1
bash scripts/ci/amd_ci_exec.sh python3 -m unittest test_bench_one_batch.TestBenchOneBatch.test_torch_compile_tp2_bs1
- name: Benchmark offline throughput (TP=2)
timeout-minutes: 25
run: |
bash scripts/amd_ci_exec.sh python3 -m unittest test_bench_serving.TestBenchServing.test_moe_offline_throughput_default
bash scripts/ci/amd_ci_exec.sh python3 -m unittest test_bench_serving.TestBenchServing.test_moe_offline_throughput_default
- name: Benchmark offline throughput (w/o RadixAttention) (TP=2)
timeout-minutes: 25
run: |
bash scripts/amd_ci_exec.sh python3 -m unittest test_bench_serving.TestBenchServing.test_moe_offline_throughput_without_radix_cache
bash scripts/ci/amd_ci_exec.sh python3 -m unittest test_bench_serving.TestBenchServing.test_moe_offline_throughput_without_radix_cache
unit-test-backend-1-gpu-amd:
if: (github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request') &&
@@ -230,17 +230,17 @@ jobs:
uses: actions/checkout@v4
- name: Start CI container
run: bash scripts/amd_ci_start_container.sh
run: bash scripts/ci/amd_ci_start_container.sh
env:
GITHUB_WORKSPACE: ${{ github.workspace }}
- name: Install dependencies
run: bash scripts/amd_ci_install_dependency.sh
run: bash scripts/ci/amd_ci_install_dependency.sh
- name: Run test
timeout-minutes: 50
run: |
bash scripts/amd_ci_exec.sh python3 run_suite.py --suite per-commit-amd --auto-partition-id ${{ matrix.part }} --auto-partition-size 7
bash scripts/ci/amd_ci_exec.sh python3 run_suite.py --suite per-commit-amd --auto-partition-id ${{ matrix.part }} --auto-partition-size 7
unit-test-backend-2-gpu-amd:
if: (github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request') &&
@@ -254,17 +254,17 @@ jobs:
uses: actions/checkout@v4
- name: Start CI container
run: bash scripts/amd_ci_start_container.sh
run: bash scripts/ci/amd_ci_start_container.sh
env:
GITHUB_WORKSPACE: ${{ github.workspace }}
- name: Install dependencies
run: bash scripts/amd_ci_install_dependency.sh
run: bash scripts/ci/amd_ci_install_dependency.sh
- name: Run test
timeout-minutes: 40
run: |
bash scripts/amd_ci_exec.sh python3 run_suite.py --suite per-commit-2-gpu-amd
bash scripts/ci/amd_ci_exec.sh python3 run_suite.py --suite per-commit-2-gpu-amd
unit-test-backend-8-gpu-amd:
if: (github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request') &&
@@ -278,22 +278,22 @@ jobs:
uses: actions/checkout@v4
- name: Start CI container
run: bash scripts/amd_ci_start_container.sh
run: bash scripts/ci/amd_ci_start_container.sh
env:
GITHUB_WORKSPACE: ${{ github.workspace }}
- name: Install dependencies
run: bash scripts/amd_ci_install_dependency.sh
run: bash scripts/ci/amd_ci_install_dependency.sh
- name: Run test
timeout-minutes: 60
run: |
bash scripts/amd_ci_exec.sh python3 run_suite.py --suite per-commit-8-gpu-amd --timeout-per-file 3600
bash scripts/ci/amd_ci_exec.sh python3 run_suite.py --suite per-commit-8-gpu-amd --timeout-per-file 3600
- name: Run CustomAllReduce test
timeout-minutes: 20
run: |
bash scripts/amd_ci_exec.sh -e CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 python3 -m unittest test_custom_allreduce.TestCustomAllReduce
bash scripts/ci/amd_ci_exec.sh -e CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 python3 -m unittest test_custom_allreduce.TestCustomAllReduce
unit-test-sgl-kernel-amd:
if: (github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request') &&
@@ -308,13 +308,13 @@ jobs:
uses: actions/checkout@v4
- name: Start CI container
run: bash scripts/amd_ci_start_container.sh
run: bash scripts/ci/amd_ci_start_container.sh
env:
GITHUB_WORKSPACE: ${{ github.workspace }}
- name: Install dependencies
run: |
bash scripts/amd_ci_install_dependency.sh
bash scripts/ci/amd_ci_install_dependency.sh
- name: Run test
timeout-minutes: 10