XingfenD/transformer_study
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
3 Commits 1 Branch 0 Tags
c57a9bf9e698f2a7393adfe8aeaef85610935804
Commit Graph

2 Commits

Author SHA1 Message Date
XingfenD c57a9bf9e6 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
 2026-07-16 15:07:47 +08:00
XingfenD 836060ecdf Initial commit: Simple Transformer implementation 2026-07-16 14:29:12 +08:00