[5/N] MoE Refactor: Update MoE parallelism arguments (#8658)

2025-08-01 01:20:03 -07:00
parent c8d3a402c1
commit 6c88f6c8d9
38 changed files with 342 additions and 299 deletions
--- a/test/srt/test_moe_deepep_eval_accuracy_large.py
+++ b/test/srt/test_moe_deepep_eval_accuracy_large.py
@@ -31,7 +31,8 @@ class TestMoEDeepEPEvalAccuracyLarge(CustomTestCase):
                "--trust-remote-code",
                "--tp",
                "8",
-                "--enable-deepep-moe",
+                "--moe-a2a-backend",
+                "deepep",
                "--cuda-graph-max-bs",
                "128",
            ],