[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/experts.py

@@ -17,7 +17,7 @@ from typing import List, Optional
 from .experts_base import BaseMoEWrapper, KExpertsCPUBuffer
 
 # Import backend implementations
-from .utils.amx import AMXMoEWrapper
+from .utils.amx import AMXMoEWrapper, RAWAMXMoEWrapper
 from .utils.llamafile import LlamafileMoEWrapper
 from .utils.moe_kernel import GeneralMoEWrapper
 
@@ -77,7 +77,7 @@ class KTMoEWrapper:
             chunked_prefill_size: Maximum prefill chunk size
             cpu_save: Whether to save weights to CPU memory
             max_deferred_experts_per_token: Number of experts per token to defer. Defaults to 0.
-            method: Backend method ("AMXINT4", "AMXINT8", "LLAMAFILE", "MOE_INT4", "MOE_INT8")
+            method: Backend method ("AMXINT4", "AMXINT8", "RAWINT4", "LLAMAFILE", "MOE_INT4", "MOE_INT8")
 
         Returns:
             An instance of the appropriate backend implementation (e.g., AMXMoEWrapper)
@@ -85,6 +85,8 @@ class KTMoEWrapper:
         # Select backend based on method
         if method in ["AMXINT4", "AMXINT8"]:
             backend_cls = AMXMoEWrapper
+        elif method == "RAWINT4":
+            backend_cls = RAWAMXMoEWrapper
         elif method == "LLAMAFILE":
             backend_cls = LlamafileMoEWrapper
         elif method in ["MOE_INT4", "MOE_INT8"]: