[Bugfix] Fix the issue of the acceptance rate decline for Qwen3-30B-A3B-EAGLE3

[zhaomingyu13]

What this PR does / why we need it?

Due to the long-term lack of synchronization with the upstream code, a problem that led to a decrease in the acceptance rate of the Qwen3-30B-A3B-EAGLE3 draft model was introduced when fixing the bug（#5967）. Now, synchronize with the upstream and fix this bug

Does this PR introduce any user-facing change?

No

How was this patch tested?

from vllm import LLM, SamplingParams

def main():
    prompts = [
        "The future of AI is",
    ]

    # Create a sampling params object.
    sampling_params = SamplingParams(temperature=0.8, top_p=0.95)
    # Create an LLM.
    llm = LLM(
            model="Qwen/Qwen3-30B-A3B",
            tensor_parallel_size=4,
            gpu_memory_utilization=0.9,
            enforce_eager=True,
            speculative_config={
                "method": "eagle3",
                "model": "AngelSlim/Qwen3-a3B_eagle3"
                "num_speculative_tokens": 3,
            },
        )

    # Generate texts from the prompts.
    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}")

• vLLM version: v0.13.0
• vLLM main: vllm-project/vllm@d682094

[github-actions]

👋 Hi! Thank you for contributing to the vLLM Ascend project. The following points will speed up your PR merge:‌‌

• A PR should do only one thing, smaller PRs enable faster reviews.
• Every PR should include unit tests and end-to-end tests ‌to ensure it works and is not broken by other future PRs.
• Write the commit message by fulfilling the PR description to help reviewer and future developers understand.

If CI fails, you can run linting and testing checks locally according Contributing and Testing.

[gemini-code-assist]

Code Review

The pull request refactors the logic for sharing embedding weights between the EAGLE/MTP model and the target model. The changes introduce more granular control over when embeddings are shared, addressing potential issues with models that might not have their own embedding layers or when their embeddings are identical to the target model's. This should help fix the acceptance rate decline by ensuring correct embedding handling.

[drslark]

Please follow the original logic.

[drslark]

Oops, it's my mistake.

[drslark]

LGTM.