chenchenghao/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 12 Packages Projects Releases Wiki Activity

Merge performance/accuracy test suites into regular stage-b suites (#17609)

Browse Source
This commit is contained in:
Alison Shao
2026-01-25 22:49:19 -08:00
committed by GitHub
parent 8c2d8b51e9
commit 30b3192039
12 changed files with 41 additions and 279 deletions
Download Patch File Download Diff File Expand all files Collapse all files
test/registered/eval/test_eval_accuracy_large.py
+2 -2
View File
@@ -19,8 +19,8 @@ from sglang.test.test_utils import (
write_github_step_summary,
)
register_cuda_ci(est_time=300, suite="stage-b-test-small-1-gpu-accuracy")
register_amd_ci(est_time=300, suite="stage-b-test-small-1-gpu-accuracy-amd")
register_cuda_ci(est_time=300, suite="stage-b-test-small-1-gpu")
register_amd_ci(est_time=300, suite="stage-b-test-small-1-gpu-amd")
class TestEvalAccuracyLarge(CustomTestCase):
test/registered/eval/test_moe_eval_accuracy_large.py
+2 -2
View File
@@ -19,8 +19,8 @@ from sglang.test.test_utils import (
write_github_step_summary,
)
register_cuda_ci(est_time=500, suite="stage-b-test-large-2-gpu-accuracy")
register_amd_ci(est_time=500, suite="stage-b-test-large-2-gpu-accuracy-amd")
register_cuda_ci(est_time=500, suite="stage-b-test-large-2-gpu")
register_amd_ci(est_time=500, suite="stage-b-test-large-2-gpu-amd")
class TestMoEEvalAccuracyLarge(CustomTestCase):
test/registered/perf/test_bench_one_batch_1gpu.py
+2 -2
View File
@@ -11,8 +11,8 @@ from sglang.test.test_utils import (
write_github_step_summary,
)
register_cuda_ci(est_time=120, suite="stage-b-test-large-1-gpu-performance")
register_amd_ci(est_time=120, suite="stage-b-test-large-1-gpu-performance-amd")
register_cuda_ci(est_time=120, suite="stage-b-test-large-1-gpu")
register_amd_ci(est_time=120, suite="stage-b-test-large-1-gpu-amd")
class TestBenchOneBatch1GPU(CustomTestCase):
test/registered/perf/test_bench_one_batch_2gpu.py
+2 -2
View File
@@ -11,8 +11,8 @@ from sglang.test.test_utils import (
write_github_step_summary,
)
register_cuda_ci(est_time=180, suite="stage-b-test-large-2-gpu-performance")
register_amd_ci(est_time=630, suite="stage-b-test-large-2-gpu-performance-amd")
register_cuda_ci(est_time=180, suite="stage-b-test-large-2-gpu")
register_amd_ci(est_time=630, suite="stage-b-test-large-2-gpu-amd")
class TestBenchOneBatch2GPU(CustomTestCase):
test/registered/perf/test_bench_serving_1gpu_large.py
+2 -2
View File
@@ -17,8 +17,8 @@ from sglang.test.test_utils import (
write_github_step_summary,
)
register_cuda_ci(est_time=300, suite="stage-b-test-large-1-gpu-performance")
register_amd_ci(est_time=300, suite="stage-b-test-large-1-gpu-performance-amd")
register_cuda_ci(est_time=300, suite="stage-b-test-large-1-gpu")
register_amd_ci(est_time=300, suite="stage-b-test-large-1-gpu-amd")
class TestBenchServing1GPULarge(CustomTestCase):
test/registered/perf/test_bench_serving_1gpu_part1.py
+2 -2
View File
@@ -19,8 +19,8 @@ from sglang.test.test_utils import (
write_github_step_summary,
)
register_cuda_ci(est_time=1000, suite="stage-b-test-large-1-gpu-performance")
register_amd_ci(est_time=1100, suite="stage-b-test-large-1-gpu-performance-amd")
register_cuda_ci(est_time=1000, suite="stage-b-test-large-1-gpu")
register_amd_ci(est_time=1100, suite="stage-b-test-large-1-gpu-amd")
class TestBenchServing1GPUPart1(CustomTestCase):
test/registered/perf/test_bench_serving_1gpu_part2.py
+2 -2
View File
@@ -19,8 +19,8 @@ from sglang.test.test_utils import (
write_github_step_summary,
)
register_cuda_ci(est_time=900, suite="stage-b-test-large-1-gpu-performance")
register_amd_ci(est_time=900, suite="stage-b-test-large-1-gpu-performance-amd")
register_cuda_ci(est_time=900, suite="stage-b-test-large-1-gpu")
register_amd_ci(est_time=900, suite="stage-b-test-large-1-gpu-amd")
class TestBenchServing1GPUPart2(CustomTestCase):
test/registered/perf/test_bench_serving_2gpu.py
+2 -2
View File
@@ -14,8 +14,8 @@ from sglang.test.test_utils import (
write_github_step_summary,
)
register_cuda_ci(est_time=600, suite="stage-b-test-large-2-gpu-performance")
register_amd_ci(est_time=600, suite="stage-b-test-large-2-gpu-performance-amd")
register_cuda_ci(est_time=600, suite="stage-b-test-large-2-gpu")
register_amd_ci(est_time=600, suite="stage-b-test-large-2-gpu-amd")
class TestBenchServing2GPU(CustomTestCase):
test/registered/perf/test_vlm_perf_5090.py
+2 -2
View File
@@ -13,8 +13,8 @@ from sglang.test.test_utils import (
write_github_step_summary,
)
register_cuda_ci(est_time=600, suite="stage-b-test-small-1-gpu-performance")
register_amd_ci(est_time=500, suite="stage-b-test-small-1-gpu-performance-amd")
register_cuda_ci(est_time=600, suite="stage-b-test-small-1-gpu")
register_amd_ci(est_time=500, suite="stage-b-test-small-1-gpu-amd")
class TestVLMPerf5090(CustomTestCase):
test/run_suite.py
+1 -4
View File
@@ -22,6 +22,7 @@ PER_COMMIT_SUITES = {
"stage-a-test-1-amd",
"stage-b-test-small-1-gpu-amd",
"stage-b-test-small-1-gpu-amd-mi35x",
"stage-b-test-large-1-gpu-amd",
"stage-b-test-large-2-gpu-amd",
"stage-b-test-small-1-gpu-performance-amd",
"stage-b-test-large-1-gpu-performance-amd",
@@ -33,12 +34,8 @@ PER_COMMIT_SUITES = {
HWBackend.CUDA: [
"stage-a-test-1",
"stage-b-test-small-1-gpu",
"stage-b-test-small-1-gpu-performance",
"stage-b-test-small-1-gpu-accuracy",
"stage-b-test-large-1-gpu",
"stage-b-test-large-1-gpu-performance",
"stage-b-test-large-2-gpu",
"stage-b-test-large-2-gpu-performance",
"stage-c-test-large-4-gpu",
"stage-b-test-4-gpu-b200",
"stage-c-test-large-4-gpu-b200",