Natural Memory NM2.1: 记忆路由器分叉、数据集缺陷修复与全轴评测证据

- 引入 MemoryRouterXL 与 v5/v6 流式多线程训练/编码管线
- 修复 prepare_memory_router_dataset 候选池重建缺陷（mega 家族 3568x 加速，输出逐字节相同）
- 修复 v5 被破坏的拒答与多跳标签（train 未知样本 319 -> 16319，multi_hop 平均正例 1.00 -> 2.00）
- 同存储预算下 V2-128 v6 逐轴 22/22 通过：Top-1 41.12% -> 94.62%，未知拒答 0.00% -> 100.00%
- 记录三条被实测推翻的显然优化（logits_to_keep=1 反而慢 55%、XL 容量未带来收益）
- 记忆手术跨架构可移植性 14/14，读写关闭时与原生模型逐位相同

evaluate_associative.py

@@ -0,0 +1,49 @@
+"""Evaluate a saved dynamic-memory checkpoint."""
+
+from __future__ import annotations
+
+import argparse
+
+import torch
+
+from .model import DynamicMemoryConfig, DynamicMemoryLM
+from .tasks import sample_associative_batch
+
+
+def main() -> None:
+    parser = argparse.ArgumentParser()
+    parser.add_argument("--checkpoint", default="V2_dpskw/checkpoints/latest.pt")
+    parser.add_argument("--batches", type=int, default=100)
+    parser.add_argument("--device", default="auto", choices=("auto", "cpu", "cuda"))
+    args = parser.parse_args()
+
+    device = torch.device("cuda" if args.device == "auto" and torch.cuda.is_available() else ("cpu" if args.device == "auto" else args.device))
+    checkpoint = torch.load(args.checkpoint, map_location=device, weights_only=False)
+    config = DynamicMemoryConfig(**checkpoint["config"])
+    model = DynamicMemoryLM(config).to(device)
+    model.load_state_dict(checkpoint["model"])
+    model.eval()
+
+    for overwrite in (False, True):
+        correct = 0
+        total = 0
+        with torch.no_grad():
+            for _ in range(args.batches):
+                batch = sample_associative_batch(
+                    batch_size=256,
+                    vocab_size=config.vocab_size,
+                    device=device,
+                    overwrite=overwrite,
+                )
+                memory = None
+                for chunk in batch.learn_chunks:
+                    memory = model(chunk, memory=memory, update_memory=True).memory
+                output = model(batch.query_input, memory=memory, update_memory=False)
+                prediction = output.logits[:, 0].argmax(dim=-1)
+                correct += int((prediction == batch.expected).sum())
+                total += batch.expected.numel()
+        print(f"overwrite={overwrite} accuracy={correct / total:.3f}")
+
+
+if __name__ == "__main__":
+    main()