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

[misc] Use --cuda-graph-max-bs-decode in tests, examples, and docs (#29591)

Browse Source
This commit is contained in:
Liangsheng Yin
2026-06-28 18:38:28 -07:00
committed by GitHub
parent 3217410cf6
commit 909123ddb8
140 changed files with 304 additions and 290 deletions
Download Patch File Download Diff File Expand all files Collapse all files
test/manual/dsv4/test_b200_pro.py
+3 -3
View File
@@ -60,7 +60,7 @@ class TestB200ProBalanced(DSV4ProAime25TestBase):
"2",
"--mem-fraction-static",
"0.82",
"--cuda-graph-max-bs",
"--cuda-graph-max-bs-decode",
"64",
"--max-running-requests",
"128",
@@ -83,7 +83,7 @@ class TestB200ProMaxThroughput(DSV4ProAime25TestBase):
"deepep",
"--mem-fraction-static",
"0.82",
"--cuda-graph-max-bs",
"--cuda-graph-max-bs-decode",
"64",
"--max-running-requests",
"256",
@@ -108,7 +108,7 @@ class TestB200ProCP(DSV4ProAime25TestBase):
"16384",
"--mem-fraction-static",
"0.78",
"--cuda-graph-max-bs",
"--cuda-graph-max-bs-decode",
"256",
"--max-running-requests",
"256",