[Spec Decode] Fix max_model_len logging in speculative config for draft model (#41571)

Signed-off-by: Lanze Liu <[email protected]>

tests/v1/spec_decode/test_max_len.py

@@ -6,6 +6,7 @@ import pytest
 
 from tests.utils import get_attn_backend_list_based_on_platform
 from vllm import LLM, SamplingParams
+from vllm.config import ModelConfig, ParallelConfig, SpeculativeConfig
 from vllm.platforms import current_platform
 from vllm.sampling_params import StructuredOutputsParams
 
@@ -77,3 +78,23 @@ def test_eagle_max_len(
             "is longer than the eagle max length"
         )
         assert o.outputs[0].text == "a b c d e " * 15
+
+
+@pytest.mark.parametrize("spec_max_model_len", [80, 150])
+def test_mtp_speculative_config_max_model_len(spec_max_model_len: int):
+    """Regression test for #41456: max_model_len in speculative config
+    should be respected for the draft model."""
+    model_config = ModelConfig(
+        model="XiaomiMiMo/MiMo-7B-Base",
+        runner="generate",
+        max_model_len=200,
+        trust_remote_code=True,
+    )
+    spec_config = SpeculativeConfig(
+        target_model_config=model_config,
+        target_parallel_config=ParallelConfig(),
+        method="mtp",
+        num_speculative_tokens=1,
+        max_model_len=spec_max_model_len,
+    )
+    assert spec_config.draft_model_config.max_model_len == spec_max_model_len

vllm/config/speculative.py

@@ -626,6 +626,7 @@ class SpeculativeConfig:
                     revision=self.revision,
                     code_revision=self.code_revision,
                     tokenizer_revision=self.target_model_config.tokenizer_revision,
+                    max_model_len=self.max_model_len,  # type: ignore[arg-type]
                     spec_target_max_model_len=self.target_model_config.max_model_len,
                     quantization=self.quantization,
                     enforce_eager=self.target_model_config.enforce_eager,
@@ -837,10 +838,17 @@ class SpeculativeConfig:
 
             return speculative_max_model_len
 
-        return min(
+        result = min(
             draft_max_model_len,
             target_max_model_len,
         )
+        if result != draft_max_model_len:
+            logger.info(
+                "Overriding draft model max model len from %d to %d",
+                draft_max_model_len,
+                result,
+            )
+        return result
 
     @staticmethod
     def _verify_and_get_draft_tp(