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

[CI] Update B200 est_times to prevent timeouts on slower machine (#22609)

Browse Source 
Co-authored-by: Alison Shao <alison.shao@MacBook-Pro-D2W773R9CD.local>
This commit is contained in:
Alison Shao
2026-04-11 21:40:34 -07:00
committed by GitHub
co-authored by Alison Shao
parent f21d23a211
commit d6c9d9116b
9 changed files with 9 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files
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=1146, suite="stage-c-test-4-gpu-b200")
register_cuda_ci(est_time=1380, 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=302, suite="stage-c-test-4-gpu-b200")
register_cuda_ci(est_time=630, 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_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=322, suite="stage-c-test-4-gpu-b200")
register_cuda_ci(est_time=550, suite="stage-c-test-4-gpu-b200")
MODEL_PATH = "nvidia/Llama-3.1-8B-Instruct-NVFP4"