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/core/executor.py

@@ -38,13 +38,11 @@ class Executor:
         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
-            )
+        input_ids = torch.tensor(
+            [t.prompt_ids[start_pos:prompt_len] for t in tasks],
+            dtype=torch.long,
+            device=self.device,
+        )
 
         task_ids = [t.task_id for t in tasks]
         page_tables = self.page_cache.make_table_tensor(task_ids, self.device)