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

[ci] split stage-c-test-4-gpu-b200 to enable a low-disk runner pool (#23417)

Browse Source 
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
Kangyan-Zhou
2026-04-21 18:33:33 -07:00
committed by GitHub
co-authored by Claude Opus 4.7
parent 6cf0b004ca
commit 77fd86f89e
15 changed files with 84 additions and 14 deletions
Download Patch File Download Diff File Expand all files Collapse all files
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=630, suite="stage-c-test-4-gpu-b200")
register_cuda_ci(est_time=630, suite="nightly-4-gpu-b200", nightly=True)
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=550, suite="stage-c-test-4-gpu-b200")
register_cuda_ci(est_time=550, suite="nightly-4-gpu-b200", nightly=True)
MODEL_PATH = "nvidia/Llama-3.1-8B-Instruct-NVFP4"