refactor: 重构 inference 模块架构，引入设计模式并分组文件

- 新增 protocol.py 协议层，Template Method 模式消除流/非流分支 45% 重复
- SSEBuilder 统一 SSE 构造，StopChecker 独立 stop_sequence 检测
- AnthropicHandler 追踪已产出文本，修复 stop 时重复 delta
- server.py 路由从约 100 行缩减至 3 行
- 拆分为 core/（cache/executor/scheduler/task）和 api/（protocol/server）
- 外部保持二级导入路径（from astrai.inference import Name）
- 删除所有分隔线注释，代码按语义自然分组

astrai/inference/core/executor.py

@@ -0,0 +1,117 @@
+import logging
+from typing import List, Optional
+
+import torch
+
+from astrai.inference.core.cache import PagedCache
+from astrai.inference.core.task import Task
+from astrai.inference.sample import sample
+from astrai.model.automodel import AutoModel
+from astrai.tokenize.tokenizer import AutoTokenizer
+
+logger = logging.getLogger(__name__)
+
+
+class Executor:
+    """Model forward passes for prefill and decode phases."""
+
+    def __init__(
+        self,
+        model: AutoModel,
+        tokenizer: AutoTokenizer,
+        page_cache: PagedCache,
+        device: Optional[str] = None,
+        dtype: Optional[torch.dtype] = None,
+    ):
+        self.model = model
+        self.tokenizer = tokenizer
+        self.page_cache = page_cache
+        self.device = device or next(model.parameters()).device
+        self.dtype = dtype or next(model.parameters()).dtype
+
+    def execute_prefill(
+        self, tasks: List[Task], prompt_len: int, start_pos: int = 0
+    ) -> None:
+        if start_pos >= prompt_len:
+            return
+
+        tasks = sorted(tasks, key=lambda t: t.task_id)
+        batch_sz = len(tasks)
+
+        seq_len = prompt_len - start_pos
+        input_ids = torch.empty(batch_sz, seq_len, dtype=torch.long, device=self.device)
+
+        for i, t in enumerate(tasks):
+            input_ids[i] = torch.tensor(
+                t.prompt_ids[start_pos:prompt_len], device=self.device
+            )
+
+        task_ids = [t.task_id for t in tasks]
+        page_tables = self.page_cache.make_table_tensor(task_ids, self.device)
+
+        with torch.inference_mode():
+            self.model(
+                input_ids,
+                position_ids=torch.arange(
+                    start_pos, prompt_len, dtype=torch.long, device=self.device
+                )
+                .unsqueeze(0)
+                .expand(batch_sz, -1),
+                paged_cache=self.page_cache.bind(page_tables, total_len=prompt_len),
+            )
+
+        for i, t in enumerate(tasks):
+            input_ids[i] = torch.tensor(
+                t.prompt_ids[start_pos:prompt_len], device=self.device
+            )
+
+        task_ids = [t.task_id for t in tasks]
+        page_tables = self.page_cache.make_table_tensor(task_ids, self.device)
+
+        with torch.inference_mode():
+            self.model(
+                input_ids,
+                position_ids=torch.arange(
+                    start_pos, prompt_len, dtype=torch.long, device=self.device
+                )
+                .unsqueeze(0)
+                .expand(batch_sz, -1),
+                paged_cache=self.page_cache.bind(page_tables, total_len=prompt_len),
+            )
+
+    def execute_decode(self, tasks: List[Task]) -> List[int]:
+        if not tasks:
+            return []
+
+        input_ids = torch.tensor(
+            [t.output_ids[-1] if t.output_ids else t.prompt_ids[-1] for t in tasks],
+            dtype=torch.long,
+            device=self.device,
+        )
+
+        position_ids = torch.tensor(
+            [t.next_pos for t in tasks], dtype=torch.long, device=self.device
+        )
+        total_len = position_ids.max().item() + 1
+
+        task_ids = [t.task_id for t in tasks]
+        page_tables = self.page_cache.make_table_tensor(task_ids, self.device)
+
+        temperatures = torch.tensor([t.temperature for t in tasks], device=self.device)
+        top_ks = torch.tensor([t.top_k for t in tasks], device=self.device)
+        top_ps = torch.tensor([t.top_p for t in tasks], device=self.device)
+
+        with torch.inference_mode():
+            outputs = self.model(
+                input_ids.unsqueeze(1),
+                paged_cache=self.page_cache.bind(page_tables, total_len=total_len),
+                position_ids=position_ids.unsqueeze(1),
+            )
+            logits = outputs["logits"][:, -1, :]
+
+        return sample(
+            logits,
+            temperature=temperatures,
+            top_k=top_ks,
+            top_p=top_ps,
+        ).tolist()