Eagle3 mm support, enablement on qwen3vl (#4848)

### What this PR does / why we need it?
follow pr
[https://github.com/vllm-project/vllm/pull/20788](https://github.com/vllm-project/vllm/pull/20788)
, Eagle3 mm support, enablement on qwen3vl
target model
[Qwen/Qwen3-VL-8B-Instruct]([https://huggingface.co/Qwen/Qwen3-VL-8B-Instruct])
eagle3
[MNN/Qwen3-VL-8B-Instruct-Eagle3](https://www.modelscope.cn/models/MNN/Qwen3-VL-8B-Instruct-Eagle3)
### Does this PR introduce _any_ user-facing change?
No
### How was this patch tested?

pytest ./tests/e2e/singlecard/test_completion_with_prompt_embeds.py -vv

vLLM with eagle3 :
```bash
vllm serve /model/Qwen3-VL-8B-Instruct   --enforce-eager   --port 9100    --max-model-len 32768   --max-num-seqs 32   --tensor-parallel-size 2   --allowed-local-media-path /model/gx/images  --speculative-config '{
    "method": "eagle3",
    "model": "/model/hf/Qwen3-VL-8B-Instruct-Eagle3",
    "num_speculative_tokens": 3
  }'
```
vLLM without eagle3 :
```bash
vllm serve /model/Qwen3-VL-8B-Instruct   --enforce-eager   --port 9100    --max-model-len 32768   --max-num-seqs 32   --tensor-parallel-size 2   --allowed-local-media-path /model/gx/images 
```

bench:
```
vllm bench serve   --backend openai-chat   --base-url http://127.0.0.1:9100   --tokenizer /model/Qwen3-VL-8B-Instruct   --endpoint /v1/chat/completions   --model /model/Qwen3-VL-8B-Instruct   --dataset-name random  --num-prompts 50   --max-concurrency 5   --temperature 0   --top-p 1.0   --seed 123
```

- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c

---------

Signed-off-by: jesse <szxfml@gmail.com>

tests/e2e/singlecard/spec_decode/test_v1_spec_decode.py

@@ -85,6 +85,14 @@ def eagle3_model_name():
     return "vllm-ascend/EAGLE3-LLaMA3.1-Instruct-8B"
 
 
+@pytest.fixture
+def vl_model_name():
+    return "Qwen/Qwen3-VL-8B-Instruct"
+
+def vl_eagle3_model_name():
+    return "MNN/Qwen3-VL-8B-Instruct-Eagle3"
+
+
 def test_ngram_correctness(
     test_prompts: list[list[dict[str, Any]]],
     sampling_config: SamplingParams,
@@ -129,6 +137,48 @@ def test_ngram_correctness(
     assert matches > int(0.66 * len(ref_outputs))
 
 
+def test_qwen3_vl_eagle_correctness(
+    test_prompts: list[list[dict[str, Any]]],
+    sampling_config: SamplingParams,
+    vl_model_name: str,
+):
+    '''
+    Compare the outputs of a original LLM and a speculative LLM
+    should be the same when using eagle speculative decoding.
+    '''
+    with VllmRunner(
+            vl_model_name,
+            max_model_len=1024,
+            cudagraph_capture_sizes=[1, 2, 4, 8],
+    ) as ref_llm:
+        ref_outputs = ref_llm.model.chat(test_prompts, sampling_config)
+
+    spec_model_name = vl_eagle3_model_name()
+    with VllmRunner(
+            vl_model_name,
+            speculative_config={
+                "method": "eagle3",
+                "model": spec_model_name,
+                "num_speculative_tokens": 2,
+            },
+            max_model_len=1024,
+            cudagraph_capture_sizes=[1, 2, 4, 8],
+    ) as runner:
+        spec_outputs = runner.model.chat(test_prompts, sampling_config)
+    matches = 0
+    misses = 0
+    for ref_output, spec_output in zip(ref_outputs, spec_outputs):
+        if ref_output.outputs[0].text == spec_output.outputs[0].text:
+            matches += 1
+        else:
+            misses += 1
+            print(f"ref_output: {ref_output.outputs[0].text}")
+            print(f"spec_output: {spec_output.outputs[0].text}")
+
+    # Heuristic: expect at least 70% of the prompts to match exactly
+    # Upon failure, inspect the outputs to check for inaccuracy.
+    assert matches > int(0.66 * len(ref_outputs))
+
 def test_suffix_correctness(
     test_prompts: list[list[dict[str, Any]]],
     sampling_config: SamplingParams,

tests/ut/spec_decode/test_eagle_proposer.py

@@ -50,6 +50,7 @@ class TestEagleProposerInitialization(TestBase):
         self.vllm_config.speculative_config.draft_model_config.get_hidden_size.return_value = 4096
         self.vllm_config.compilation_config.mode = CompilationMode.VLLM_COMPILE
         self.vllm_config.model_config.enforce_eager = False
+        self.vllm_config.model_config.uses_mrope = False
         self.vllm_config.speculative_config.enforce_eager = False
         self.vllm_config.scheduler_config.async_scheduling = False
         init_ascend_config(self.vllm_config)
@@ -156,6 +157,7 @@ class TestEagleProposerLoadModel(TestBase):
         }]
 
         mock_model = MagicMock()
+        mock_model.supports_multimodal = False
         mock_model.model.embed_tokens = MagicMock()
         mock_model.lm_head = MagicMock()
         mock_model.multimodal_cpu_fields = None
@@ -226,7 +228,7 @@ class TestEagleProposerLoadModel(TestBase):
         self.proposer.name = SpecDcodeType.EAGLE
 
         self.proposer.load_model(mock_model)
-        mock_model.get_language_model.assert_called_once()
+        self.assertEqual(mock_model.get_language_model.call_count, 2)
         self.assertIs(self.proposer.model.lm_head,
                       mock_model.get_language_model.return_value.lm_head)