添加KV Cache支持：实现prefill/decode阶段分离

- MultiHeadAttention类添加KV cache机制
- TransformerBlock支持use_cache参数
- SimpleTransformer新增prefill和decode方法
- 添加InferenceEngine推理引擎类
- 更新example.py演示推理过程
- 更新README.md文档

README.md

@@ -1,11 +1,11 @@
 # Simple Transformer
 
-A minimal Transformer implementation using NumPy.
+A minimal Transformer implementation using NumPy with **KV Cache** support for efficient inference.
 
 ## Files
 
-- `transformer.py` - Core Transformer model implementation
-- `example.py` - Usage example
+- `transformer.py` - Core Transformer model implementation with KV Cache
+- `example.py` - Usage examples (training & inference)
 
 ## Usage
 
@@ -21,6 +21,21 @@ The implementation includes:
 - **Feed-Forward Network**: Two-layer fully connected network with ReLU activation
 - **Layer Normalization**: Applied after each sub-layer
 - **Positional Encoding**: Sinusoidal position embeddings
+- **KV Cache**: Efficient inference with prefill/decode separation
+
+## Inference: Prefill vs Decode
+
+### Prefill Stage
+- Process the complete input prompt in parallel
+- Initialize KV cache for all layers
+- Generate the first token
+- Computation: O(n²)
+
+### Decode Stage
+- Process one token at a time
+- Reuse cached Key and Value tensors
+- Only compute new Query
+- Computation: O(n) per step
 
 ## Model Parameters
 
@@ -32,4 +47,9 @@ Default configuration:
 - Feed-forward dimension: 2048
 - Max sequence length: 100
 
-Total parameters: ~19.4M
+Total parameters: ~19.4M
+
+## Classes
+
+- `SimpleTransformer` - Transformer model with prefill/decode methods
+- `InferenceEngine` - Manages inference process with KV cache