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

[CI] Temporarily disable flaky test_priority_metrics on CUDA (#20075)

Browse Source 
Co-authored-by: Alison Shao <alisonshao@Mac.attlocal.net>
This commit is contained in:
Alison Shao
2026-03-06 20:34:45 -08:00
committed by GitHub
co-authored by Alison Shao
parent 925185f9ec
commit c584158135
2 changed files with 10 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
test/registered/metrics/test_priority_metrics.py
+5 -1
View File
@@ -16,7 +16,11 @@ from sglang.test.test_utils import (
popen_launch_server, popen_launch_server,
) )
register_cuda_ci(est_time=60, suite="stage-b-test-small-1-gpu") register_cuda_ci(
est_time=60,
suite="stage-b-test-small-1-gpu",
disabled="Flaky: no TTFT histogram samples. See https://github.com/sgl-project/sglang/actions/runs/22787468608/job/66118130037",
)
register_amd_ci(est_time=60, suite="stage-b-test-small-1-gpu-amd") register_amd_ci(est_time=60, suite="stage-b-test-small-1-gpu-amd")
_MODEL_NAME = "Qwen/Qwen3-0.6B" _MODEL_NAME = "Qwen/Qwen3-0.6B"
test/registered/sessions/test_session_latency.py
+5 -1
View File
@@ -35,7 +35,11 @@ from sglang.test.test_utils import (
popen_launch_server, popen_launch_server,
) )
register_cuda_ci(est_time=100, suite="stage-b-test-large-1-gpu") register_cuda_ci(
est_time=100,
suite="stage-b-test-large-1-gpu",
disabled="Flaky: streaming vs regular session 1/300 turns differ. See https://github.com/sgl-project/sglang/actions/runs/22790998325/job/66117795513",
)
NUM_TURNS = 300 NUM_TURNS = 300
INPUT_LEN = 16 INPUT_LEN = 16