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

chore: update CI test est_time values (#22565)

Browse Source 
Co-authored-by: Cheng Wan <chwan@rice.edu>
Co-authored-by: sglang-bot <sglang-bot@users.noreply.github.com>
Co-authored-by: Cheng Wan <54331508+ch-wan@users.noreply.github.com>
This commit is contained in:
sglang-bot
2026-04-10 18:15:02 -07:00
committed by GitHub
co-authored by Cheng Wan sglang-bot Cheng Wan
parent b5e4ae7b1a
commit 265696b176
250 changed files with 251 additions and 251 deletions
Download Patch File Download Diff File Expand all files Collapse all files
test/registered/mla/test_flashmla.py
+1 -1
View File
@@ -21,7 +21,7 @@ from sglang.test.test_utils import (
)
# FlashMLA attention backend tests with MTP speculative decoding
register_cuda_ci(est_time=284, suite="stage-b-test-1-gpu-large")
register_cuda_ci(est_time=296, suite="stage-b-test-1-gpu-large")
class TestFlashMLAAttnBackend(unittest.TestCase):
test/registered/mla/test_mla.py
+1 -1
View File
@@ -12,7 +12,7 @@ from sglang.test.test_utils import (
)
# MLA attention test with MGSM evaluation
register_cuda_ci(est_time=194, suite="stage-b-test-1-gpu-large")
register_cuda_ci(est_time=174, suite="stage-b-test-1-gpu-large")
register_amd_ci(est_time=1100, suite="stage-b-test-1-gpu-small-amd")
test/registered/mla/test_mla_deepseek_v3.py
+1 -1
View File
@@ -16,7 +16,7 @@ from sglang.test.test_utils import (
)
# DeepSeek-V3 MLA tests with torch compile, FA3, and MTP speculative decoding
register_cuda_ci(est_time=442, suite="stage-b-test-1-gpu-large")
register_cuda_ci(est_time=543, suite="stage-b-test-1-gpu-large")
register_amd_ci(
est_time=221,
suite="stage-b-test-1-gpu-small-amd",
test/registered/mla/test_mla_flashinfer.py
+1 -1
View File
@@ -15,7 +15,7 @@ from sglang.test.test_utils import (
)
# FlashInfer MLA backend tests with MTP speculative decoding
register_cuda_ci(est_time=302, suite="stage-b-test-1-gpu-large")
register_cuda_ci(est_time=256, suite="stage-b-test-1-gpu-large")
class TestFlashinferMLA(CustomTestCase):
test/registered/mla/test_mla_fp8.py
+1 -1
View File
@@ -12,7 +12,7 @@ from sglang.test.test_utils import (
)
# MLA FP8 KV cache test with MGSM evaluation
register_cuda_ci(est_time=77, suite="stage-b-test-1-gpu-large")
register_cuda_ci(est_time=106, suite="stage-b-test-1-gpu-large")
register_amd_ci(est_time=800, suite="stage-b-test-1-gpu-small-amd")
test/registered/mla/test_mla_int8_deepseek_v3.py
+1 -1
View File
@@ -16,7 +16,7 @@ from sglang.test.test_utils import (
)
# DeepSeek-V3 INT8 quantization tests (channel and block INT8)
register_cuda_ci(est_time=290, suite="stage-b-test-1-gpu-large")
register_cuda_ci(est_time=282, suite="stage-b-test-1-gpu-large")
class TestMLADeepseekV3ChannelInt8(CustomTestCase):