[Fix] Add speculative_draft_model_revision to server_args (#5255)

Signed-off-by: Devashish Lal <devashish@rivosinc.com>
2025-09-05 04:45:46 -07:00
parent df97b31f37
commit 13705dae06
13 changed files with 68 additions and 45 deletions
--- a/test/srt/test_dp_attention.py
+++ b/test/srt/test_dp_attention.py
@@ -74,7 +74,7 @@ class TestDPAttentionDP2TP2DeepseekV3MTP(CustomTestCase):
            "4",
            "--speculative-num-draft-tokens",
            "4",
-            "--speculative-draft",
+            "--speculative-draft-model-path",
            DEFAULT_MODEL_NAME_FOR_TEST_MLA_NEXTN,
            "--tp-size",
            "2",