fix: 修复推理引擎 batch decode 中多项正确性与并发问题

- scheduler: decode 分组由幂次分桶改为精确 next_pos，消除 KV cache 位置错乱
- task: activate() 加锁操作 active_tasks，消除数据竞争
- engine: wait_completion 加超时，防止分配失败时永久死锁
- sample: TopKStrategy 向量化为 per-sample threshold，尊重各 task 的 top_k
- cache: Storage.write/gather 中 -1 页改用 mask 处理，防数据污染
- executor: prefill 逐 task 循环改为单次 tensor 调用

astrai/inference/engine.py

@@ -59,9 +59,15 @@ class GenerateResult:
     def wait(self, timeout: Optional[float] = None) -> bool:
         return self._event.wait(timeout=timeout)
 
-    def wait_completion(self) -> None:
+    def wait_completion(self, timeout: float = 300.0) -> None:
         with self._cond:
-            self._cond.wait_for(lambda: self._completed >= self._total)
+            if not self._cond.wait_for(
+                lambda: self._completed >= self._total, timeout=timeout
+            ):
+                raise TimeoutError(
+                    f"Generation timeout after {timeout}s "
+                    f"({self._completed}/{self._total} completed)"
+                )
 
     def get_results(self) -> List[str]:
         with self._cond:
@@ -267,7 +273,12 @@ class InferenceEngine:
             prompts, max_tokens, temperature, top_p, top_k
         )
 
-        result.wait_completion()
+        try:
+            result.wait_completion()
+        except TimeoutError:
+            for tid in task_ids:
+                self.scheduler.remove_task(tid)
+            raise
 
         for tid in task_ids:
             self.scheduler.remove_task(tid)