[Feature] Add avx-based kimi-k2 support (#1656)

* support Kimi-K2-Thinking original weight
fix amx kernel bug

* update k2 avx kernel.

* feat: add CPUInfer write buffer task

* [feat]: add kimi k2 cpu write buffer support

- Implement write_weights_to_buffer function in k2-moe.hpp for extracting GPU expert weights
- Fix down (w2) weight column-wise slicing for different TP configurations
- Support three TP scenarios: cpu_tp == gpu_tp, cpu_tp > gpu_tp, cpu_tp < gpu_tp
- Add comprehensive test cases for weight extraction validation
- Ensure compatibility with Kimi model's MoE architecture

* [fix]: correct write_weight_scale_to_buffer expert offset calculation

Fixed the bug in write_weight_scale_to_buffer_task where expert offsets in GPU buffers were incorrectly calculated. Changed from using per_expert_gpu sizes to using full gpu_tp sizes, ensuring correct memory layout for multi-expert scenarios.

Also added benchmark scripts for k2 moe and write buffer operations, and cleaned up debug output in test files.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

* [feat]: add write buffer wrapper

* [fix] fix comment

---------

Co-authored-by: ouqingliang <1692110604@qq.com>
Co-authored-by: Claude <noreply@anthropic.com>

kt-kernel/python/utils/__init__.py

@@ -4,13 +4,15 @@
 Utilities for kt_kernel package.
 """
 
-from .amx import AMXMoEWrapper
+from .amx import AMXMoEWrapper, RAWAMXMoEWrapper
 from .llamafile import LlamafileMoEWrapper
-from .loader import SafeTensorLoader, GGUFLoader
+from .loader import SafeTensorLoader, GGUFLoader, CompressedSafeTensorLoader
 
 __all__ = [
     "AMXMoEWrapper",
+    "RAWAMXMoEWrapper",
     "LlamafileMoEWrapper",
     "SafeTensorLoader",
+    "CompressedSafeTensorLoader",
     "GGUFLoader",
 ]