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

Update CI threshold & Improve code style (#2159)

Browse Source
This commit is contained in:
Lianmin Zheng
2024-11-24 06:29:38 -08:00
committed by GitHub
parent e3938b2f9c
commit 5652c56535
8 changed files with 126 additions and 41 deletions
Download Patch File Download Diff File Expand all files Collapse all files

56
.github/workflows/pr-test.yml vendored
View File

@@ -50,7 +50,7 @@ jobs:
timeout-minutes: 25
run: |
cd test/srt
python3 run_suite.py --suite minimal --range-begin 0 --range-end 5
python3 run_suite.py --suite minimal --range-begin 0 --range-end 6
unit-test-backend-part-2:
if: github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request'
@@ -67,7 +67,7 @@ jobs:
timeout-minutes: 25
run: |
cd test/srt
python3 run_suite.py --suite minimal --range-begin 5 --range-end 14
python3 run_suite.py --suite minimal --range-begin 6 --range-end 14
unit-test-backend-part-3:
if: github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request'
@@ -103,6 +103,31 @@ jobs:
cd test/srt
python3 run_suite.py --suite minimal --range-begin 21
unit-test-backend-2-gpu-part-1:
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: |
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
performance-test-1-gpu-part-1:
if: github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request'
runs-on: 1-gpu-runner
@@ -178,6 +203,12 @@ jobs:
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: |
@@ -190,12 +221,6 @@ jobs:
cd test/srt
python3 -m unittest test_bench_serving.TestBenchServing.test_moe_offline_throughput_without_radix_cache
- name: Benchmark single latency (TP=2)
timeout-minutes: 10
run: |
cd test/srt
python3 -m unittest test_bench_one_batch.TestBenchOneBatch.test_moe_default
accuracy-test-1-gpu:
if: github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request'
runs-on: 1-gpu-runner
@@ -238,23 +263,10 @@ jobs:
cd test/srt
python3 test_moe_eval_accuracy_large.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: Evaluate data parallelism accuracy (DP=2)
timeout-minutes: 10
run: |
cd test/srt
python3 test_data_parallelism.py
finish:
needs: [
unit-test-frontend, unit-test-backend-part-1, unit-test-backend-part-2, unit-test-backend-part-3, unit-test-backend-part-4,
unit-test-backend-2-gpu-part-1,
performance-test-1-gpu-part-1, performance-test-1-gpu-part-2, performance-test-2-gpu,
accuracy-test-1-gpu, accuracy-test-2-gpu
]