minke.yu/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 13 Packages Projects Releases Wiki Activity

chore: update CI test est_time values (#38238)

Browse Source 
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
Download Patch File Download Diff File Expand all files Collapse all files
test/registered/radix_cache/test_int8_mamba_checkpoint_e2e.py
+1 -1
View File
@@ -38,7 +38,7 @@ from sglang.test.test_utils import (
terminate_and_kill_process_tree,
)
register_cuda_ci(est_time=800, stage="extra-b", runner_config="4-gpu-h100")
register_cuda_ci(est_time=344, stage="extra-b", runner_config="4-gpu-h100")
class TestInt8MambaCheckpointE2E(KLDivergenceMixin, DefaultServerBase):
test/registered/radix_cache/test_mamba2_extra_buffer_kl.py
+1 -1
View File
@@ -26,7 +26,7 @@ from sglang.test.ci.ci_register import register_cuda_ci
from sglang.test.kits.kl_divergence_kit import KLDivergenceMixin
from sglang.test.server_fixtures.default_fixture import DefaultServerBase
register_cuda_ci(est_time=600, stage="extra-a", runner_config="1-gpu-large")
register_cuda_ci(est_time=154, stage="extra-a", runner_config="1-gpu-large")
class TestMamba2ExtraBufferKL(KLDivergenceMixin, DefaultServerBase):
test/registered/radix_cache/test_radix_attention.py
+1 -1
View File
@@ -18,7 +18,7 @@ from sglang.test.test_utils import (
)
# RadixAttention server integration tests
register_cuda_ci(est_time=100, stage="base-b", runner_config="1-gpu-small")
register_cuda_ci(est_time=148, stage="base-b", runner_config="1-gpu-small")
register_amd_ci(est_time=100, suite="stage-b-test-1-gpu-small-amd")
register_cpu_ci(est_time=405, suite="stage-b-test-cpu-intel")
test/registered/radix_cache/test_radix_cache_hit.py
+1 -1
View File
@@ -15,7 +15,7 @@ from sglang.test.test_utils import (
terminate_and_kill_process_tree,
)
register_cuda_ci(est_time=55, stage="base-b", runner_config="1-gpu-small")
register_cuda_ci(est_time=71, stage="base-b", runner_config="1-gpu-small")
register_amd_ci(est_time=55, suite="stage-b-test-1-gpu-small-amd")
register_cpu_ci(est_time=113, suite="stage-b-test-cpu-intel")
test/registered/radix_cache/test_swa_radix_cache_kl.py
+1 -1
View File
@@ -6,7 +6,7 @@ from sglang.test.server_fixtures.default_fixture import DefaultServerBase
MODEL = "openai/gpt-oss-20b"
register_cuda_ci(est_time=151, stage="base-b", runner_config="1-gpu-large")
register_cuda_ci(est_time=198, stage="base-b", runner_config="1-gpu-large")
register_cpu_ci(est_time=1602, suite="stage-b-test-cpu-intel")
test/registered/radix_cache/unified_radix_tree/linker/test_unified_cache_linker_kl_dsv4.py
+1 -1
View File
@@ -20,7 +20,7 @@ DSV4_FLASH_MODEL = os.environ.get(
)
DSV4_FLASH_LAUNCH_TIMEOUT = 3600
register_cuda_ci(est_time=1500, stage="extra-b", runner_config="4-gpu-h100")
register_cuda_ci(est_time=210, stage="extra-b", runner_config="4-gpu-h100")
class TestDeepSeekV4FlashUnifiedCacheLinkerKL(
test/registered/radix_cache/unified_radix_tree/linker/test_unified_cache_linker_kl_glm52.py
+1 -1
View File
@@ -18,7 +18,7 @@ from sglang.test.test_utils import (
GLM52_MODEL = os.environ.get("SGLANG_LINKER_GLM52_MODEL", "zai-org/GLM-5.2-FP8")
GLM52_LAUNCH_TIMEOUT = 3600
register_cuda_ci(est_time=1200, stage="extra-b", runner_config="8-gpu-h200")
register_cuda_ci(est_time=383, stage="extra-b", runner_config="8-gpu-h200")
class TestGLM52UnifiedCacheLinkerKL(UnifiedRadixTreeTestMixin, CustomTestCase):
test/registered/radix_cache/unified_radix_tree/test_unified_radix_cache_hicache_pp_kl.py
+1 -1
View File
@@ -19,7 +19,7 @@ from sglang.test.test_utils import (
terminate_and_kill_process_tree,
)
register_cuda_ci(est_time=900, stage="base-c", runner_config="4-gpu-h100")
register_cuda_ci(est_time=738, stage="base-c", runner_config="4-gpu-h100")
QWEN3_32B_MODEL = "Qwen/Qwen3-32B"
test/registered/radix_cache/unified_radix_tree/test_unified_radix_cache_kl_cp.py
+1 -1
View File
@@ -11,7 +11,7 @@ from sglang.test.test_utils import (
terminate_and_kill_process_tree,
)
register_cuda_ci(est_time=950, stage="extra-b", runner_config="4-gpu-h100")
register_cuda_ci(est_time=346, stage="extra-b", runner_config="4-gpu-h100")
QWEN3_32B_MODEL = "Qwen/Qwen3-32B"
test/registered/radix_cache/unified_radix_tree/test_unified_radix_cache_kl_dcp.py
+1 -1
View File
@@ -24,7 +24,7 @@ from sglang.test.test_utils import (
terminate_and_kill_process_tree,
)
register_cuda_ci(est_time=1500, stage="extra-b", runner_config="4-gpu-b200")
register_cuda_ci(est_time=280, stage="extra-b", runner_config="4-gpu-b200")
KIMI_LINEAR_MODEL = "moonshotai/Kimi-Linear-48B-A3B-Instruct"
DCP_SIZE = 4
test/registered/radix_cache/unified_radix_tree/test_unified_radix_cache_kl_dsv4.py
+1 -1
View File
@@ -25,7 +25,7 @@ DSV4_FLASH_MODEL = "sgl-project/DeepSeek-V4-Flash-FP8"
DSV4_DSPARK_MODEL = "deepseek-ai/DeepSeek-V4-Flash-DSpark"
DSV4_FLASH_LAUNCH_TIMEOUT = 3600
register_cuda_ci(est_time=4800, stage="extra-b", runner_config="4-gpu-h100")
register_cuda_ci(est_time=1865, stage="extra-b", runner_config="4-gpu-h100")
def _assert_dsv4_decode_cached_tokens(result, history_len, output_len, label):
test/registered/radix_cache/unified_radix_tree/test_unified_radix_cache_kl_dsv4_pp.py
+1 -1
View File
@@ -4,7 +4,7 @@ import test_unified_radix_cache_kl_dsv4 as dsv4_kl
from sglang.test.ci.ci_register import register_cuda_ci
register_cuda_ci(est_time=900, stage="extra-b", runner_config="8-gpu-h200")
register_cuda_ci(est_time=478, stage="extra-b", runner_config="8-gpu-h200")
class TestUnifiedDeepSeekV4FlashHiCachePP4TP2(
test/registered/radix_cache/unified_radix_tree/test_unified_radix_cache_kl_full.py
+1 -1
View File
@@ -12,7 +12,7 @@ from sglang.test.test_utils import (
unified_radix_tree_server_env,
)
register_cuda_ci(est_time=500, stage="base-b", runner_config="2-gpu-large")
register_cuda_ci(est_time=415, stage="base-b", runner_config="2-gpu-large")
register_amd_ci(est_time=800, suite="stage-b-test-2-gpu-large-amd")
FULL_MODEL = "Qwen/Qwen3-32B"
test/registered/radix_cache/unified_radix_tree/test_unified_radix_cache_kl_glm52.py
+1 -1
View File
@@ -21,7 +21,7 @@ from sglang.test.test_utils import (
GLM5_MODEL = "zai-org/GLM-5.2-FP8"
GLM5_LAUNCH_TIMEOUT = 3600
register_cuda_ci(est_time=900, stage="extra-b", runner_config="8-gpu-h200")
register_cuda_ci(est_time=340, stage="extra-b", runner_config="8-gpu-h200")
class TestGLM5UnifiedRadixCacheL3Accuracy(AccuracyTwoPassMixin, CustomTestCase):
test/registered/radix_cache/unified_radix_tree/test_unified_radix_cache_kl_hybrid_bitexact.py
+1 -1
View File
@@ -73,7 +73,7 @@ from sglang.test.test_utils import (
unified_radix_tree_server_env,
)
register_cuda_ci(est_time=2300, stage="base-b", runner_config="1-gpu-large")
register_cuda_ci(est_time=790, stage="base-b", runner_config="1-gpu-large")
_MODEL_PATH = os.environ.get("INKLING_TEST_MODEL_PATH", "thinkingmachines/Inkling")
_MODEL_REVISION = os.environ.get("INKLING_TEST_MODEL_REVISION", "test")
test/registered/radix_cache/unified_radix_tree/test_unified_radix_cache_kl_mamba.py
+1 -1
View File
@@ -21,7 +21,7 @@ from sglang.test.test_utils import (
terminate_and_kill_process_tree,
)
register_cuda_ci(est_time=800, stage="extra-b", runner_config="4-gpu-h100")
register_cuda_ci(est_time=742, stage="extra-b", runner_config="4-gpu-h100")
MAMBA_MODEL = "Qwen/Qwen3-Next-80B-A3B-Instruct-FP8"
MAMBA_CHUNK_SIZE = 64
test/registered/radix_cache/unified_radix_tree/test_unified_radix_cache_kl_swa.py
+1 -1
View File
@@ -11,7 +11,7 @@ from sglang.test.test_utils import (
terminate_and_kill_process_tree,
)
register_cuda_ci(est_time=250, stage="base-b", runner_config="2-gpu-large")
register_cuda_ci(est_time=301, stage="base-b", runner_config="2-gpu-large")
SWA_MODEL = "openai/gpt-oss-20b"