[KV-Sharing] Support KV-Sharing feature in CLA models

[MengqingCao]

What this PR does / why we need it?

Support KV-Sharing feature in CLA models

Does this PR introduce any user-facing change?

How was this patch tested?

test with Gemma3n

import os

os.environ["VLLM_USE_MODELSCOPE"] = "True"
os.environ["VLLM_WORKER_MULTIPROC_METHOD"] = "spawn"
os.environ["VLLM_VERSION"] = "0.12.0"

from vllm import LLM, SamplingParams
def main():
    prompts = [
        "窗前明月光，",
        "The president of the United States is Mr.",
        "The capital of France is",
        "The future of AI is",
        "感时花溅泪，",
        "家书抵万金啥意思？",
        "plz tell me a story: ",
    ]

    # Create a sampling params object.
    sampling_params = SamplingParams(max_tokens=100, temperature=0.6, top_k=40, top_p=0.95)

    # Create an LLM.
    llm = LLM(
        model="/home/cache/modelscope/models/google/gemma-3n-E2B-it",
              tensor_parallel_size=4,
              trust_remote_code=True,
              max_model_len=1024,
              gpu_memory_utilization=0.8,
              cuda_graph_sizes=[16]
              )

    # Generate texts from the prompts.
    outputs = llm.generate(prompts, sampling_params)
    for output in outputs:
        prompt = output.prompt
        generated_text = output.outputs[0].text
        print(f"Prompt: {prompt!r}, Generated text: {generated_text!r}")


if __name__ == "__main__":
    main()

• vLLM version: v0.11.0
• vLLM main: vllm-project/vllm@83f478b

[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.