chore: update CI test est_time values (#38238)

Co-authored-by: sglang-bot <sglang-bot@users.noreply.github.com>
This commit is contained in:
sglang-bot
2026-09-06 17:49:41 -07:00
committed by GitHub
co-authored by sglang-bot
parent 15aa2fb843
commit 6252993afe
1016 changed files with 1051 additions and 1051 deletions
+1 -1
View File
@@ -33,7 +33,7 @@ from sglang.srt.mem_cache.memory_pool import HybridLinearKVPool
from sglang.test.ci.ci_register import register_cpu_ci
from sglang.test.test_utils import CustomTestCase
register_cpu_ci(est_time=10, suite="base-a-test-cpu")
register_cpu_ci(est_time=11, suite="base-a-test-cpu")
DCP_SIZES = [1, 2, 3, 4, 8]
LENS = list(range(0, 41))
+1 -1
View File
@@ -55,7 +55,7 @@ from sglang.test.test_utils import (
# ---------------------------------------------------------------------------
# CI registration — only TestDSV31DCP8TP8GSM8K runs in CI
# ---------------------------------------------------------------------------
register_cuda_ci(est_time=600, stage="extra-b", runner_config="8-gpu-h200")
register_cuda_ci(est_time=213, stage="extra-b", runner_config="8-gpu-h200")
DEEPSEEK_V31_MODEL_PATH = "deepseek-ai/DeepSeek-V3.1"
+1 -1
View File
@@ -20,7 +20,7 @@ from sglang.test.test_utils import (
popen_launch_server,
)
register_cuda_ci(est_time=240, stage="extra-b", runner_config="4-gpu-b200")
register_cuda_ci(est_time=105, stage="extra-b", runner_config="4-gpu-b200")
KIMI_LINEAR_MODEL = "moonshotai/Kimi-Linear-48B-A3B-Instruct"
CUDA_GRAPH_MAX_BS_DECODE = 256
@@ -22,7 +22,7 @@ from sglang.test.test_utils import (
popen_launch_server,
)
register_cuda_ci(est_time=350, stage="extra-b", runner_config="4-gpu-b200")
register_cuda_ci(est_time=201, stage="extra-b", runner_config="4-gpu-b200")
KIMI_LINEAR_MODEL = "moonshotai/Kimi-Linear-48B-A3B-Instruct"
GSM8K_SCORE_THRESHOLD = 0.88
@@ -23,7 +23,7 @@ from sglang.srt.model_executor.forward_batch_info import ForwardMode
from sglang.test.ci.ci_register import register_cuda_ci
from sglang.test.test_utils import CustomTestCase
register_cuda_ci(est_time=60, stage="base-b", runner_config="4-gpu-b200")
register_cuda_ci(est_time=10, stage="base-b", runner_config="4-gpu-b200")
NUM_DRAFT_TOKENS = 8
DCP_SIZE = 4