minke.yu/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 13 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/registered/radix_cache/unified_radix_tree/test_unified_radix_cache_hicache_pp_kl.py
+1 -1
View File
@@ -75,7 +75,7 @@ class TestUnifiedQwen3HiCachePP(UnifiedRadixTreeTestMixin, CustomTestCase):
"2",
"--mem-fraction-static",
"0.8",
"--cuda-graph-max-bs",
"--cuda-graph-max-bs-decode",
"32",
"--max-running-requests",
str(cls.max_running_requests),
test/registered/radix_cache/unified_radix_tree/test_unified_radix_cache_kl_cp.py
+1 -1
View File
@@ -43,7 +43,7 @@ class TestUnifiedQwen3HiCacheCP(UnifiedRadixTreeTestMixin, CustomTestCase):
"--enable-prefill-context-parallel",
"--mem-fraction-static",
"0.8",
"--cuda-graph-max-bs",
"--cuda-graph-max-bs-decode",
"32",
"--max-running-requests",
str(cls.max_running_requests),