chore: update CI test est_time values (#38238)

Co-authored-by: sglang-bot <sglang-bot@users.noreply.github.com>

test/registered/unit/entrypoints/anthropic/test_serving.py

@@ -24,7 +24,7 @@ from sglang.srt.parser.template_detection import (  # noqa: E402
 )
 from sglang.test.ci.ci_register import register_cpu_ci  # noqa: E402
 
-register_cpu_ci(est_time=1, suite="base-a-test-cpu")
+register_cpu_ci(est_time=11, suite="base-a-test-cpu")
 
 
 class _FakeOpenAIServingChat:

test/registered/unit/entrypoints/openai/test_audio_chunking.py

@@ -24,7 +24,7 @@ from sglang.srt.entrypoints.openai.audio_chunking import (
 from sglang.test.ci.ci_register import register_cpu_ci
 from sglang.test.test_utils import CustomTestCase
 
-register_cpu_ci(est_time=4, suite="base-a-test-cpu")
+register_cpu_ci(est_time=11, suite="base-a-test-cpu")
 
 SR = 16000
 

test/registered/unit/entrypoints/openai/test_exa_search.py

@@ -16,7 +16,7 @@ from sglang.srt.entrypoints.search.exa_client import (
 from sglang.srt.entrypoints.tool import HarmonyBrowserTool
 from sglang.test.ci.ci_register import register_cpu_ci
 
-register_cpu_ci(est_time=3, suite="base-a-test-cpu")
+register_cpu_ci(est_time=10, suite="base-a-test-cpu")
 
 
 class ExaClientTestCase(unittest.TestCase):

test/registered/unit/entrypoints/openai/test_responses_protocol.py

@@ -12,7 +12,7 @@ from sglang.srt.entrypoints.openai.protocol import (
 from sglang.test.ci.ci_register import register_cpu_ci
 from sglang.test.test_utils import CustomTestCase
 
-register_cpu_ci(est_time=7, suite="base-a-test-cpu")
+register_cpu_ci(est_time=10, suite="base-a-test-cpu")
 
 
 def _in_progress_response(request: ResponsesRequest) -> ResponsesResponse:

test/registered/unit/entrypoints/openai/test_serving_chat.py

@@ -49,7 +49,7 @@ from sglang.srt.sampling.sampling_params import (
 from sglang.srt.utils import get_or_create_event_loop
 from sglang.test.ci.ci_register import register_cpu_ci
 
-register_cpu_ci(est_time=11, suite="base-a-test-cpu")
+register_cpu_ci(est_time=13, suite="base-a-test-cpu")
 
 # Every spec resolve_chat_encoding_spec can return; pinned by the guard below.
 _ALL_CHAT_ENCODING_SPECS = ("dsv4", "dsv32", "inkling", "kimi_k3")

test/registered/unit/entrypoints/openai/test_serving_embedding.py

@@ -58,7 +58,7 @@ from sglang.srt.entrypoints.openai.serving_embedding import OpenAIServingEmbeddi
 from sglang.srt.managers.io_struct import EmbeddingReqInput
 from sglang.test.ci.ci_register import register_cpu_ci
 
-register_cpu_ci(est_time=10, suite="base-a-test-cpu")
+register_cpu_ci(est_time=11, suite="base-a-test-cpu")
 register_cpu_ci(est_time=6, suite="stage-b-test-cpu-intel")
 
 

test/registered/unit/entrypoints/openai/test_serving_responses.py

@@ -29,7 +29,7 @@ from sglang.srt.sampling.sampling_params import (
 from sglang.test.ci.ci_register import register_cpu_ci
 from sglang.test.test_utils import CustomTestCase
 
-register_cpu_ci(est_time=7, suite="base-a-test-cpu")
+register_cpu_ci(est_time=10, suite="base-a-test-cpu")
 
 
 class InputMessageConstructionTestCase(CustomTestCase):

test/registered/unit/entrypoints/openai/test_serving_responses_stream.py

@@ -14,7 +14,7 @@ from sglang.srt.entrypoints.openai.protocol import ResponsesRequest
 from sglang.test.ci.ci_register import register_cpu_ci
 from sglang.test.test_utils import CustomTestCase
 
-register_cpu_ci(est_time=7, suite="base-a-test-cpu")
+register_cpu_ci(est_time=10, suite="base-a-test-cpu")
 
 
 class NonHarmonyStreamTestCase(CustomTestCase):

test/registered/unit/entrypoints/openai/test_serving_transcription.py

@@ -36,7 +36,7 @@ from sglang.srt.utils import get_or_create_event_loop
 from sglang.test.ci.ci_register import register_cpu_ci
 from sglang.test.test_utils import CustomTestCase
 
-register_cpu_ci(est_time=4, suite="base-a-test-cpu")
+register_cpu_ci(est_time=12, suite="base-a-test-cpu")
 
 
 def _chunk(text: str, finish: str = None) -> dict:

test/registered/unit/entrypoints/openai/test_transcription_adapters.py

@@ -24,7 +24,7 @@ from sglang.srt.entrypoints.openai.transcription_adapters import (
 from sglang.test.ci.ci_register import register_cpu_ci
 from sglang.test.test_utils import CustomTestCase
 
-register_cpu_ci(est_time=4, suite="base-a-test-cpu")
+register_cpu_ci(est_time=11, suite="base-a-test-cpu")
 
 
 # Per-second scaling rate every speech-LM adapter uses for max_new_tokens.

test/registered/unit/entrypoints/openai/test_whisper_adapter.py

@@ -21,7 +21,7 @@ from sglang.srt.entrypoints.openai.transcription_adapters.whisper import (
 from sglang.test.ci.ci_register import register_cpu_ci
 from sglang.test.test_utils import CustomTestCase
 
-register_cpu_ci(est_time=2, suite="base-a-test-cpu")
+register_cpu_ci(est_time=11, suite="base-a-test-cpu")
 
 
 class TestWhisperParseFusedOutput(CustomTestCase):

test/registered/unit/entrypoints/test_effective_state_surfaces.py

@@ -31,7 +31,7 @@ from sglang.srt.entrypoints.engine import Engine
 from sglang.test.ci.ci_register import register_cpu_ci
 from sglang.test.test_utils import CustomTestCase
 
-register_cpu_ci(est_time=3, suite="base-a-test-cpu")
+register_cpu_ci(est_time=13, suite="base-a-test-cpu")
 
 _PACKAGE_ROOT = pathlib.Path(sglang.__file__).resolve().parent
 _RUST_MODEL_INFO = (

test/registered/unit/entrypoints/test_grpc_bridge.py

@@ -7,7 +7,7 @@ from sglang.srt.entrypoints.grpc_bridge import RuntimeHandle
 from sglang.test.ci.ci_register import register_cpu_ci
 from sglang.test.test_utils import CustomTestCase
 
-register_cpu_ci(est_time=1, suite="base-a-test-cpu")
+register_cpu_ci(est_time=10, suite="base-a-test-cpu")
 
 
 class _ChunkStatus(enum.Enum):

test/registered/unit/entrypoints/test_http2_server_config.py

@@ -5,7 +5,7 @@ from unittest.mock import patch
 from sglang.srt.entrypoints.http_server import _run_granian_server
 from sglang.test.ci.ci_register import register_cpu_ci
 
-register_cpu_ci(est_time=2, suite="base-a-test-cpu")
+register_cpu_ci(est_time=12, suite="base-a-test-cpu")
 
 
 @unittest.skipUnless(

test/registered/unit/entrypoints/test_http_server_warmup.py

@@ -9,7 +9,7 @@ from sglang.srt.entrypoints.http_server import (
 )
 from sglang.test.ci.ci_register import register_cpu_ci
 
-register_cpu_ci(est_time=5, suite="base-a-test-cpu")
+register_cpu_ci(est_time=12, suite="base-a-test-cpu")
 
 
 class TestDisaggregationServerWarmup(unittest.IsolatedAsyncioTestCase):

test/registered/unit/entrypoints/test_server_info.py

@@ -35,7 +35,7 @@ from sglang.srt.server_args import ServerArgs
 from sglang.test.ci.ci_register import register_cpu_ci
 from sglang.test.test_utils import CustomTestCase
 
-register_cpu_ci(est_time=5, suite="base-a-test-cpu")
+register_cpu_ci(est_time=13, suite="base-a-test-cpu")
 
 
 def _stub_tokenizer_manager(

test/registered/unit/entrypoints/test_server_warmup.py

@@ -13,7 +13,7 @@ from sglang.srt.entrypoints.http_server import (
 from sglang.test.ci.ci_register import register_cpu_ci
 from sglang.test.test_utils import CustomTestCase
 
-register_cpu_ci(est_time=5, suite="base-a-test-cpu")
+register_cpu_ci(est_time=12, suite="base-a-test-cpu")
 
 
 class TestVlmWarmupImage(CustomTestCase):

test/registered/unit/entrypoints/test_ssl_cert_refresher.py

@@ -8,7 +8,7 @@ from sglang.srt.entrypoints.ssl_utils import SSLCertRefresher
 from sglang.test.ci.ci_register import register_cpu_ci
 from sglang.test.test_utils import CustomTestCase
 
-register_cpu_ci(est_time=14, suite="base-a-test-cpu")
+register_cpu_ci(est_time=17, suite="base-a-test-cpu")
 
 
 def _make_temp_pem(content: bytes) -> str:

test/registered/unit/entrypoints/test_v1_loads_aggregate.py

@@ -31,7 +31,7 @@ from sglang.test.test_utils import CustomTestCase, maybe_stub_sgl_kernel
 maybe_stub_sgl_kernel()
 
 
-register_cpu_ci(est_time=10, suite="base-a-test-cpu")
+register_cpu_ci(est_time=11, suite="base-a-test-cpu")
 
 
 def _temp_path() -> str: