[BugFix] Support setting tp=1 for the Eagle draft model to take effect (#6097)

According to the official documentation, the parameter
"draft_tensor_parallel_size": 1 is supposed to be applied to the Eagle3
model. However, based on actual debugging, it was found that the number
of tensor parallelisms (tp) of the Eagle model is consistent with that
of the target model. The setting of tp for the draft model did not take
effect as expected.

**Note:** This feature has not been superimposed and tested with `sp`
and `dp`. It will be adapted later
No
```python
from vllm import LLM, SamplingParams

def main():
    prompts = [
        "The future of AI is",
    ]
    sampling_params = SamplingParams(temperature=0.8, top_p=0.95)
    llm = LLM(
            model="meta-llama/Llama-3.1-8B-Instruct",
            tensor_parallel_size=4,
            gpu_memory_utilization=0.9,
            enforce_eager=True,
            speculative_config={
                "method": "eagle3",
                "model": "yuhuili/EAGLE3-LLaMA3.1-Instruct-8B"
                "draft_tensor_parallel_size": 1,
                "num_speculative_tokens": 3,
            },
        )
    outputs = llm.generate(prompts, sampling_params)
    print(f"Outputs: {outputs}")
    for output in outputs:
        prompt = output.prompt
        generated_text = output.outputs[0].text
        print(f"Prompt: {prompt!r}, Generated text: {generated_text!r}")
```

Fixes vllm-project/vllm#31345

### What this PR does / why we need it?

### Does this PR introduce _any_ user-facing change?

### How was this patch tested?

- vLLM version: v0.13.0
- vLLM main:
d68209402d

Signed-off-by: zhaomingyu <zhaomingyu13@h-partners.com>
Co-authored-by: drslark <slarksblood@qq.com>

tests/ut/spec_decode/test_eagle_proposer.py

@@ -27,6 +27,8 @@ class TestEagleProposerInitialization(TestBase):
         self.vllm_config.model_config.dtype = torch.float16
         self.vllm_config.model_config.max_model_len = 2048
         self.vllm_config.model_config.uses_mrope = False
+        self.vllm_config.parallel_config.tensor_parallel_size = 1
+        self.vllm_config.speculative_config.draft_tensor_parallel_size = 1
         self.vllm_config.speculative_config.num_speculative_tokens = 2
         self.vllm_config.speculative_config.speculative_token_tree = str([
             (i + 1) * (0, ) for i in range(2)
@@ -115,6 +117,8 @@ class TestEagleProposerLoadModel(TestBase):
         self.vllm_config.model_config.dtype = torch.float16
         self.vllm_config.model_config.max_model_len = 2048
         self.vllm_config.model_config.uses_mrope = False
+        self.vllm_config.parallel_config.tensor_parallel_size = 1
+        self.vllm_config.speculative_config.draft_tensor_parallel_size = 1
         self.vllm_config.speculative_config.num_speculative_tokens = 2
         self.vllm_config.speculative_config.speculative_token_tree = str([
             (i + 1) * (0, ) for i in range(2)
@@ -256,6 +260,8 @@ class TestEagleProposerDummyRun(TestBase):
         self.vllm_config.model_config.max_model_len = 2048
         self.vllm_config.model_config.uses_mrope = False
         self.vllm_config.model_config.use_mla = False
+        self.vllm_config.parallel_config.tensor_parallel_size = 1
+        self.vllm_config.speculative_config.draft_tensor_parallel_size = 1
         self.vllm_config.speculative_config.speculative_token_tree = str([
             (i + 1) * (0, ) for i in range(4)
         ])
@@ -370,6 +376,8 @@ class TestEagleProposerHelperMethods(TestBase):
         self.vllm_config.model_config.dtype = torch.float16
         self.vllm_config.model_config.max_model_len = 2048
         self.vllm_config.model_config.uses_mrope = False
+        self.vllm_config.parallel_config.tensor_parallel_size = 1
+        self.vllm_config.speculative_config.draft_tensor_parallel_size = 1
         self.vllm_config.speculative_config.num_speculative_tokens = 2
         self.vllm_config.speculative_config.speculative_token_tree = str([
             (i + 1) * (0, ) for i in range(2)

tests/ut/spec_decode/test_mtp_proposer.py

@@ -42,6 +42,9 @@ class TestMtpProposer:
         config.model_config.max_model_len = 2048
         config.model_config.uses_mrope = False
         config.model_config.hf_text_config = None
+        config.model_config.hf_config = None
+        config.parallel_config.tensor_parallel_size = 1
+        config.speculative_config.draft_tensor_parallel_size = 1
 
         config.load_config = None