feat: use XGrammar V4.1 DSML parameter constraints (#39026)

Co-authored-by: yuchuan <yuchuan.7streams@gmail.com>
Co-authored-by: Xinyuan Tong <115166877+JustinTong0323@users.noreply.github.com>
Co-authored-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
This commit is contained in:
Yixin Dong
2026-09-21 12:12:28 -07:00
committed by GitHub
co-authored by yuchuan Xinyuan Tong Xinyuan Tong
parent f0940fe3a6
commit ae7a516ba7
17 changed files with 380 additions and 97 deletions
@@ -50,6 +50,8 @@ class TestDPAttentionDP2TP2(
timeout=DEFAULT_TIMEOUT_FOR_SERVER_LAUNCH,
other_args=[
"--trust-remote-code",
"--constrained-json-max-whitespace-cnt",
"4",
"--tp",
"2",
"--enable-dp-attention",