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

[CI] Update est_time for 64 tests based on actual elapsed times (#22305)

Browse Source 
Co-authored-by: Alison Shao <alison.shao@Mac.lan>
Co-authored-by: Alison Shao <alison.shao@MacBook-Pro-D2W773R9CD.local>
This commit is contained in:
Alison Shao
2026-04-09 20:31:37 -07:00
committed by GitHub
co-authored by Alison Shao Alison Shao
parent 89553ff82b
commit 45b0182205
61 changed files with 61 additions and 61 deletions
Download Patch File Download Diff File Expand all files Collapse all files
test/registered/quant/test_awq.py
+1 -1
View File
@@ -13,7 +13,7 @@ from sglang.test.test_utils import (
popen_launch_server,
)
register_cuda_ci(est_time=700, suite="stage-b-test-1-gpu-large")
register_cuda_ci(est_time=260, suite="stage-b-test-1-gpu-large")
register_amd_ci(est_time=200, suite="stage-b-test-1-gpu-large-amd")
test/registered/quant/test_deepseek_v32_fp4_4gpu.py
+1 -1
View File
@@ -13,7 +13,7 @@ from sglang.test.test_utils import (
write_github_step_summary,
)
register_cuda_ci(est_time=1200, suite="stage-c-test-4-gpu-b200")
register_cuda_ci(est_time=530, suite="stage-c-test-4-gpu-b200")
FULL_DEEPSEEK_V3_FP4_MODEL_PATH = "nvidia/DeepSeek-V3.2-NVFP4"
SERVER_LAUNCH_TIMEOUT = 1200
test/registered/quant/test_deepseek_v32_fp4_mtp_4gpu.py
+1 -1
View File
@@ -16,7 +16,7 @@ from sglang.test.test_utils import (
write_github_step_summary,
)
register_cuda_ci(est_time=1200, suite="stage-c-test-4-gpu-b200")
register_cuda_ci(est_time=610, suite="stage-c-test-4-gpu-b200")
FULL_DEEPSEEK_V3_FP4_MODEL_PATH = "nvidia/DeepSeek-V3.2-NVFP4"
SERVER_LAUNCH_TIMEOUT = 1200
test/registered/quant/test_deepseek_v3_fp4_4gpu.py
+1 -1
View File
@@ -14,7 +14,7 @@ from sglang.test.test_utils import (
write_github_step_summary,
)
register_cuda_ci(est_time=1200, suite="stage-c-test-4-gpu-b200")
register_cuda_ci(est_time=450, suite="stage-c-test-4-gpu-b200")
FULL_DEEPSEEK_V3_FP4_MODEL_PATH = "nvidia/DeepSeek-V3-0324-FP4"
SERVER_LAUNCH_TIMEOUT = 1200
test/registered/quant/test_fp8_blockwise_gemm.py
+1 -1
View File
@@ -12,7 +12,7 @@ from sglang.test.test_utils import (
try_cached_model,
)
register_cuda_ci(est_time=420, suite="stage-c-test-4-gpu-b200")
register_cuda_ci(est_time=400, suite="stage-c-test-4-gpu-b200")
MODEL_PATH = "Qwen/Qwen3-4B-Instruct-2507-FP8"
MXFP8_MODEL_PATH = "zianglih/Qwen3-4B-Instruct-2507-MXFP8"
test/registered/quant/test_marlin_moe.py
+1 -1
View File
@@ -12,7 +12,7 @@ from sglang.test.ci.ci_register import register_cuda_ci
from sglang.test.test_marlin_utils import awq_marlin_quantize, marlin_quantize
from sglang.test.test_utils import CustomTestCase
register_cuda_ci(est_time=200, suite="stage-b-test-1-gpu-small")
register_cuda_ci(est_time=130, suite="stage-b-test-1-gpu-small")
set_global_server_args_for_scheduler(object.__new__(ServerArgs))
test/registered/quant/test_nvfp4_gemm.py
+1 -1
View File
@@ -12,7 +12,7 @@ from sglang.test.test_utils import (
try_cached_model,
)
register_cuda_ci(est_time=360, suite="stage-c-test-4-gpu-b200")
register_cuda_ci(est_time=300, suite="stage-c-test-4-gpu-b200")
MODEL_PATH = "nvidia/Llama-3.1-8B-Instruct-NVFP4"
test/registered/quant/test_quantization.py
+1 -1
View File
@@ -16,7 +16,7 @@ from sglang.test.test_utils import (
write_results_to_json,
)
register_cuda_ci(est_time=370, suite="stage-b-test-1-gpu-large")
register_cuda_ci(est_time=270, suite="stage-b-test-1-gpu-large")
MODEL_SCORE_THRESHOLDS = {
# Baselines observed with gsm8k 5-shot concatenated format via chat API,
test/registered/quant/test_torchao.py
+1 -1
View File
@@ -5,7 +5,7 @@ import requests
from sglang import Engine
from sglang.test.ci.ci_register import register_amd_ci, register_cuda_ci
register_cuda_ci(est_time=200, suite="stage-b-test-1-gpu-small")
register_cuda_ci(est_time=140, suite="stage-b-test-1-gpu-small")
register_amd_ci(est_time=230, suite="stage-b-test-1-gpu-small-amd")
from sglang.lang.chat_template import get_chat_template_by_model_path
from sglang.srt.utils import kill_process_tree
test/registered/quant/test_w4a8_deepseek_v3.py
+1 -1
View File
@@ -19,7 +19,7 @@ from sglang.test.test_utils import (
write_github_step_summary,
)
register_cuda_ci(est_time=520, suite="stage-c-test-8-gpu-h20")
register_cuda_ci(est_time=700, suite="stage-c-test-8-gpu-h20")
class TestDeepseekV3W4afp8(CustomTestCase):