Add chat template renderer from llama.cpp

[nguyenhoangthuan99]

Replace jinja2cpp with llama.cpp for chat template parsing

Summary

This PR replaces the jinja2cpp library with code derived from the llama.cpp project for parsing chat templates. This change significantly reduces our binary size and improves the reliability of template parsing.

Changes

• Removed jinja2cpp library and related dependencies
• Integrated chat template parsing functionality from llama.cpp
• Updated relevant code to use the new parsing method
• Added appropriate license and attribution for llama.cpp code

Benefits

1. Reduced Binary Size: Eliminates more space from our binary file.
2. Improved Reliability: The llama.cpp parsing method has shown better consistency in handling our chat templates compared to jinja2cpp, which occasionally failed to parse correctly.
3. Simplified Dependencies: Removes a complex external library, potentially reducing build times and complexity.

Related Issues

Fix #1063

Before add custom chat template renderer

After

[namchuai]

✅ lgtm

[dan-menlo]

Lgtm