docs: 修正文档中与源码不符的类名、方法签名和模块归属

- Transformer/DecoderBlock/GQA/RotaryEmbedding forward 签名 start_pos → position_ids

- _Result → GenerateResult

- save_h5/load_h5 从 serialization 移至 dataset 模块

- PagedCache UML 移除内部 PagePool 属性

- 修正 Layer 数不一致（24 vs 32）及 decode 位置分组描述

- 更新文档时间为 2026-05-14

scripts/tools/generate.py

@@ -26,7 +26,9 @@ def processor(
     model.to(device="cuda", dtype=torch.bfloat16)
 
     # Create inference engine
-    engine = InferenceEngine(model=model, tokenizer=tokenizer, max_batch_size=batch_size)
+    engine = InferenceEngine(
+        model=model, tokenizer=tokenizer, max_batch_size=batch_size
+    )
 
     with open(input_json_file, "r", encoding="utf-8") as f:
         input_data = [json.loads(line) for line in f]