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

[AMD] register 4 2-gpu tests to stage-b-test-2-gpu-large-amd (#28344)

Browse Source
This commit is contained in:
Michael
2026-06-16 21:58:34 -07:00
committed by GitHub
parent 66ac385f52
commit a2aa51c818
4 changed files with 8 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files
test/registered/attention/test_gemma4_swa_triton_oob_regression.py
+2 -1
View File
@@ -15,7 +15,7 @@ import unittest
import requests import requests
from sglang.srt.utils import kill_process_tree from sglang.srt.utils import kill_process_tree
from sglang.test.ci.ci_register import register_cuda_ci from sglang.test.ci.ci_register import register_amd_ci, register_cuda_ci
from sglang.test.test_utils import ( from sglang.test.test_utils import (
DEFAULT_TIMEOUT_FOR_SERVER_LAUNCH, DEFAULT_TIMEOUT_FOR_SERVER_LAUNCH,
DEFAULT_URL_FOR_TEST, DEFAULT_URL_FOR_TEST,
@@ -24,6 +24,7 @@ from sglang.test.test_utils import (
) )
register_cuda_ci(est_time=107, stage="base-b", runner_config="2-gpu-large") register_cuda_ci(est_time=107, stage="base-b", runner_config="2-gpu-large")
register_amd_ci(est_time=160, suite="stage-b-test-2-gpu-large-amd")
PROMPT = ( PROMPT = (
test/registered/radix_cache/unified_radix_tree/test_unified_radix_cache_kl_full.py
+2 -1
View File
@@ -1,7 +1,7 @@
import unittest import unittest
from sglang.srt.utils import kill_process_tree from sglang.srt.utils import kill_process_tree
from sglang.test.ci.ci_register import register_cuda_ci from sglang.test.ci.ci_register import register_amd_ci, register_cuda_ci
from sglang.test.kits.unified_radix_cache_kit import UnifiedRadixTreeTestMixin from sglang.test.kits.unified_radix_cache_kit import UnifiedRadixTreeTestMixin
from sglang.test.kl_multiturn_utils import get_input_ids from sglang.test.kl_multiturn_utils import get_input_ids
from sglang.test.test_utils import ( from sglang.test.test_utils import (
@@ -12,6 +12,7 @@ from sglang.test.test_utils import (
) )
register_cuda_ci(est_time=250, stage="base-b", runner_config="2-gpu-large") register_cuda_ci(est_time=250, stage="base-b", runner_config="2-gpu-large")
register_amd_ci(est_time=400, suite="stage-b-test-2-gpu-large-amd")
FULL_MODEL = "Qwen/Qwen3-32B" FULL_MODEL = "Qwen/Qwen3-32B"
test/registered/rl/test_patch_torch.py
+2 -1
View File
@@ -7,9 +7,10 @@ import torch
import torch.multiprocessing as mp import torch.multiprocessing as mp
from sglang.srt.utils.patch_torch import monkey_patch_torch_reductions from sglang.srt.utils.patch_torch import monkey_patch_torch_reductions
from sglang.test.ci.ci_register import register_cuda_ci from sglang.test.ci.ci_register import register_amd_ci, register_cuda_ci
register_cuda_ci(est_time=15, stage="base-b", runner_config="2-gpu-large") register_cuda_ci(est_time=15, stage="base-b", runner_config="2-gpu-large")
register_amd_ci(est_time=30, suite="stage-b-test-2-gpu-large-amd")
class TestReleaseMemoryOccupation(unittest.TestCase): class TestReleaseMemoryOccupation(unittest.TestCase):
test/registered/scheduler/test_load_snapshot_server.py
+2 -1
View File
@@ -10,7 +10,7 @@ import unittest
import urllib.request import urllib.request
from sglang.srt.utils import kill_process_tree from sglang.srt.utils import kill_process_tree
from sglang.test.ci.ci_register import register_cuda_ci from sglang.test.ci.ci_register import register_amd_ci, register_cuda_ci
from sglang.test.test_utils import ( from sglang.test.test_utils import (
DEFAULT_SMALL_MODEL_NAME_FOR_TEST, DEFAULT_SMALL_MODEL_NAME_FOR_TEST,
DEFAULT_TIMEOUT_FOR_SERVER_LAUNCH, DEFAULT_TIMEOUT_FOR_SERVER_LAUNCH,
@@ -20,6 +20,7 @@ from sglang.test.test_utils import (
) )
register_cuda_ci(est_time=300, stage="base-b", runner_config="2-gpu-large") register_cuda_ci(est_time=300, stage="base-b", runner_config="2-gpu-large")
register_amd_ci(est_time=450, suite="stage-b-test-2-gpu-large-amd")
def _query_loads(base_url, retries=5, interval=2.0): def _query_loads(base_url, retries=5, interval=2.0):