From b73c44b5459de8da041e7ff5f31dc7a80acd6ac3 Mon Sep 17 00:00:00 2001 From: Alison Shao <54658187+alisonshao@users.noreply.github.com> Date: Mon, 27 Apr 2026 15:27:15 -0700 Subject: [PATCH] test: relax TestMLADeepseekV3.test_gsm8k threshold 0.62 -> 0.60 (#23879) --- test/registered/mla/test_mla_deepseek_v3.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/test/registered/mla/test_mla_deepseek_v3.py b/test/registered/mla/test_mla_deepseek_v3.py index c0a56c9e3..3f8be91d3 100644 --- a/test/registered/mla/test_mla_deepseek_v3.py +++ b/test/registered/mla/test_mla_deepseek_v3.py @@ -56,7 +56,7 @@ class TestMLADeepseekV3(CustomTestCase): metrics = run_eval(args) print(metrics) - self.assertGreater(metrics["score"], 0.62) + self.assertGreater(metrics["score"], 0.60) @unittest.skipIf(is_in_ci(), "To reduce the CI execution time.")