chore: update CI test est_time values (#23785)
Co-authored-by: sglang-bot <sglang-bot@users.noreply.github.com>
This commit is contained in:
@@ -21,7 +21,7 @@ from sglang.test.test_utils import (
|
||||
)
|
||||
|
||||
# FlashMLA attention backend tests with MTP speculative decoding
|
||||
register_cuda_ci(est_time=700, suite="stage-b-test-1-gpu-large")
|
||||
register_cuda_ci(est_time=314, suite="stage-b-test-1-gpu-large")
|
||||
|
||||
|
||||
class TestFlashMLAAttnBackend(unittest.TestCase):
|
||||
|
||||
@@ -12,7 +12,7 @@ from sglang.test.test_utils import (
|
||||
)
|
||||
|
||||
# MLA attention test with MGSM evaluation
|
||||
register_cuda_ci(est_time=174, suite="stage-b-test-1-gpu-large")
|
||||
register_cuda_ci(est_time=181, suite="stage-b-test-1-gpu-large")
|
||||
register_amd_ci(est_time=1100, suite="stage-b-test-1-gpu-small-amd")
|
||||
|
||||
|
||||
|
||||
@@ -15,7 +15,7 @@ from sglang.test.test_utils import (
|
||||
)
|
||||
|
||||
# FlashInfer MLA backend tests with MTP speculative decoding
|
||||
register_cuda_ci(est_time=256, suite="stage-b-test-1-gpu-large")
|
||||
register_cuda_ci(est_time=260, suite="stage-b-test-1-gpu-large")
|
||||
|
||||
|
||||
class TestFlashinferMLA(CustomTestCase):
|
||||
|
||||
@@ -13,7 +13,7 @@ from sglang.test.test_utils import (
|
||||
)
|
||||
|
||||
# MLA FP8 KV cache test with MGSM evaluation
|
||||
register_cuda_ci(est_time=106, suite="stage-b-test-1-gpu-large")
|
||||
register_cuda_ci(est_time=104, suite="stage-b-test-1-gpu-large")
|
||||
register_amd_ci(est_time=800, suite="stage-b-test-1-gpu-small-amd")
|
||||
|
||||
|
||||
|
||||
@@ -16,7 +16,7 @@ from sglang.test.test_utils import (
|
||||
)
|
||||
|
||||
# DeepSeek-V3 INT8 quantization tests (channel and block INT8)
|
||||
register_cuda_ci(est_time=282, suite="stage-b-test-1-gpu-large")
|
||||
register_cuda_ci(est_time=313, suite="stage-b-test-1-gpu-large")
|
||||
|
||||
|
||||
class TestMLADeepseekV3ChannelInt8(CustomTestCase):
|
||||
|
||||
Reference in New Issue
Block a user