[NPU] Reuse prefill of acc lib for pipeline

[rnwang04]

Description

1. Why the change?

Accelerate prefill of NPU pipeline.
Work with https://github.com/intel-analytics/llm.cpp/pull/598

2. User API changes

See example.

3. Summary of the change

• Reuse prefill of acc lib for pipeline
• Modify generate function for corresponding adaptation
• Update embedding weight from input to const
• Update examples
• change max-output-len to max-context-len

4. How to test?

• Unit test: Please manually trigger the PR Validation here by inputting the PR number (e.g., 1234). And paste your action link here once it has been successfully finished.
• Application test

5. Demo output

[rnwang04]

PR validation is passed: https://github.com/intel-analytics/ipex-llm-workflow/actions/runs/11545625174/job/32132875794

[rnwang04]

Performance validation is updated here : https://github.com/analytics-zoo/nano/issues/1687#issuecomment-2440336530

[jason-dai]

LGTM