feat: 支持 cuda / mps / cpu 三后端，Mac 上可用 MPS 训练

移除"训练必须有 Nvidia GPU"的硬性守卫，改为按后端能力分派。

- utils/device: resolve_device("auto") 按 cuda > mps > cpu 挑最快的可用后端；
  显式指定不可用的后端时直接报错，不会悄悄退回 CPU——训练慢几十倍却不吭声是最坏的情况
- AMP 随后端取默认值：CUDA 开、MPS 关。MPS 上 autocast 数值正常但实测更慢
  （tiny_conv @128²：fp32 76 ms/步、fp16 90 ms、bf16 108 ms），需要时 amp: true 可强开
- PeakMemory 统一显存峰值统计：CUDA 读内置计数器，MPS 无峰值 API 改用逐 step 采样
  （是下界，日志与产出里已标注）
- profile_inference 支持 MPS，并提示 torch.profiler 没有 MPS 的 ProfilerActivity，
  算子明细只反映 CPU 侧下发耗时
- train.py / eval.py 新增 --device，配置默认改为 auto
- check_env 改为列出全部可用后端与 auto 的选择结果

实测：tiny_conv 训练在 MPS 上比 CPU 快约 32 倍。

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>

tests/test_simclr.py

@@ -13,7 +13,6 @@ from PIL import Image  # noqa: E402
 from engine.simclr import SimCLRTrainer, nt_xent_loss  # noqa: E402
 from models.heads.projection import ProjectionHead  # noqa: E402
 from models.registry import BACKBONES  # noqa: E402
-from utils.device import NoNvidiaGpuError  # noqa: E402
 
 
 def test_nt_xent_is_minimal_when_views_agree():
@@ -105,12 +104,46 @@ def test_simclr_trainer_runs_and_saves_backbone_only(tiny_image_dir, tmp_path):
     backbone.load_state_dict(state["model"])  # 能被干净地加载回去
 
 
+def test_simclr_saves_intermediate_checkpoints(tiny_image_dir, tmp_path):
+    """中途落盘：跑到一半被打断也要能拿到权重（此前只在全部 epoch 跑完后才存）。"""
+    from torch.utils.data import DataLoader
+
+    from datasets.unlabeled import UnlabeledImageDataset, unlabeled_collate
+
+    dataset = UnlabeledImageDataset(
+        tiny_image_dir,
+        transforms=[{"name": "Resize", "size": [32, 32]}, {"name": "ToTensor"}],
+        views=2,
+    )
+    loader = DataLoader(dataset, batch_size=4, shuffle=True, drop_last=True, collate_fn=unlabeled_collate)
+    backbone = BACKBONES.build({"name": "tiny_conv", "widths": [8, 16], "depths": [1, 1]})
+    work_dir = tmp_path / "run"
+
+    trainer = SimCLRTrainer(
+        backbone,
+        loader,
+        {"epochs": 4, "amp": False, "log_interval": 100, "save_interval": 2,
+         "projection": {"hidden_channels": 16, "out_channels": 8}},
+        torch.device("cpu"),
+        work_dir,
+    )
+    # 手动走前两个 epoch，模拟"训练中途"
+    trainer.train_one_epoch(0)
+    trainer.train_one_epoch(1)
+    path = trainer.save_backbone(1)
+
+    assert path.exists()
+    assert torch.load(path, map_location="cpu", weights_only=False)["epochs"] == 2
+
+    trainer.fit()  # 完整跑完后 epochs 应更新
+    assert torch.load(path, map_location="cpu", weights_only=False)["epochs"] == 4
+
+
 def test_cluster_script_simclr_branch_end_to_end(tiny_image_dir, tmp_path, monkeypatch):
     """method=simclr 全流程：训练 -> 存权重 -> 抽特征 -> 聚类 -> 产出。"""
     sys.path.insert(0, "scripts")
     import cluster_unlabeled as cu
 
-    monkeypatch.setattr(cu, "require_cuda", lambda: ["FAKE-GPU"])
     work_dir = tmp_path / "run"
     monkeypatch.setattr(
         sys, "argv",
@@ -130,19 +163,25 @@ def test_cluster_script_simclr_branch_end_to_end(tiny_image_dir, tmp_path, monke
     assert (work_dir / "clusters" / "cluster_00").is_dir()
 
 
-def test_simclr_branch_is_blocked_without_gpu(tiny_image_dir, tmp_path, monkeypatch):
-    """无 Nvidia GPU 时 simclr 分支必须被守卫拦下（pretrained 分支不受影响）。"""
+def test_simclr_runs_on_the_resolved_device(tiny_image_dir, tmp_path, monkeypatch):
+    """method=simclr 在本机自动选中的后端上（MPS / CUDA / CPU）都应能跑通。"""
     sys.path.insert(0, "scripts")
     import cluster_unlabeled as cu
 
-    def refuse():
-        raise NoNvidiaGpuError("没有 Nvidia GPU")
+    from utils.device import describe_device, resolve_device
 
-    monkeypatch.setattr(cu, "require_cuda", refuse)
+    device = resolve_device("auto")
+    work_dir = tmp_path / "auto_run"
     monkeypatch.setattr(
         sys, "argv",
         ["cluster_unlabeled.py", "--config", "configs/cluster/film.yaml",
-         "--work-dir", str(tmp_path / "run"), "--root", str(tiny_image_dir),
-         "--set", "device=cpu", "method=simclr", "loader.num_workers=0"],
+         "--work-dir", str(work_dir), "--root", str(tiny_image_dir), "--set",
+         "method=simclr", "loader.num_workers=0", "loader.batch_size=4",
+         "simclr.epochs=1", "simclr.batch_size=4",
+         "simclr.backbone.widths=[8,16]", "simclr.backbone.depths=[1,1]",
+         "simclr.projection.hidden_channels=16", "simclr.projection.out_channels=8",
+         "num_clusters=2", "n_init=2"],
     )
-    assert cu.main() == 1
+
+    assert cu.main() == 0, f"在 {describe_device(device)} 上跑失败"
+    assert (work_dir / "simclr_backbone.pth").exists()