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_device.py

@@ -0,0 +1,112 @@
+"""设备解析：cuda / mps / cpu 三后端的选择、AMP 默认值与显存统计。"""
+
+import pytest
+
+torch = pytest.importorskip("torch")
+
+from utils.device import (  # noqa: E402
+    BACKEND_PRIORITY,
+    DeviceNotAvailableError,
+    PeakMemory,
+    amp_supported,
+    available_backends,
+    default_amp,
+    describe_device,
+    memory_stats,
+    pin_memory_supported,
+    resolve_amp,
+    resolve_device,
+    synchronize,
+)
+
+
+def test_available_backends_is_ordered_and_always_has_cpu():
+    backends = available_backends()
+    assert backends[-1] == "cpu"
+    assert backends == [b for b in BACKEND_PRIORITY if b in backends]
+    assert len(set(backends)) == len(backends)
+
+
+def test_auto_picks_the_highest_priority_available_backend():
+    device = resolve_device("auto")
+    assert device.type == available_backends()[0]
+    assert resolve_device("") == device  # 空串等同 auto
+
+
+def test_cpu_is_always_resolvable():
+    assert resolve_device("cpu").type == "cpu"
+
+
+def test_explicit_backend_matches_hardware_or_raises():
+    """显式请求不可用的后端必须报错，不能悄悄退回 CPU——那会让训练慢几十倍还不吭声。"""
+    for backend in ("cuda", "mps"):
+        if backend in available_backends():
+            assert resolve_device(backend).type == backend
+        else:
+            with pytest.raises(DeviceNotAvailableError, match=backend):
+                resolve_device(backend)
+
+
+def test_unknown_device_raises():
+    with pytest.raises(DeviceNotAvailableError, match="未知设备"):
+        resolve_device("tpu")
+
+
+def test_amp_defaults_follow_the_backend():
+    # CUDA 有 tensor core，默认开；MPS 上 autocast 实测更慢，默认关；CPU 不支持
+    assert default_amp("cuda") is True
+    assert default_amp("mps") is False
+    assert default_amp("cpu") is False
+    assert amp_supported("cuda") and amp_supported("mps")
+    assert not amp_supported("cpu")
+
+
+def test_resolve_amp_handles_auto_and_explicit():
+    assert resolve_amp("auto", "cuda") is True
+    assert resolve_amp("auto", "mps") is False
+    assert resolve_amp(None, "mps") is False
+    assert resolve_amp(True, "mps") is True  # 显式打开，MPS 支持 autocast
+    assert resolve_amp(True, "cpu") is False  # CPU 不支持，显式打开也无效
+    assert resolve_amp(False, "cuda") is False
+
+
+def test_pin_memory_only_for_cuda():
+    assert pin_memory_supported("cuda")
+    assert not pin_memory_supported("mps")
+    assert not pin_memory_supported("cpu")
+
+
+def test_describe_device_is_readable():
+    assert describe_device("cpu") == "CPU"
+    assert "MPS" in describe_device("mps")
+
+
+def test_memory_stats_shape_per_backend():
+    assert memory_stats("cpu") == {}
+    stats = memory_stats(resolve_device("auto"))
+    device_type = resolve_device("auto").type
+    if device_type == "cuda":
+        assert {"allocated_mb", "reserved_mb", "peak_allocated_mb"} <= set(stats)
+    elif device_type == "mps":
+        assert {"allocated_mb", "driver_allocated_mb"} <= set(stats)
+
+
+def test_peak_memory_tracks_growth_on_accelerators():
+    device = resolve_device("auto")
+    peak = PeakMemory(device)
+
+    if device.type == "cpu":
+        assert peak.peak_mb == 0.0 and peak.reserved_mb == 0.0
+        return
+
+    # MPS 没有峰值 API，靠采样，所以峰值是下界（exact=False）
+    assert peak.exact == (device.type != "mps")
+    buffer = torch.empty(8 * 1024 * 1024 // 4, device=device)  # 约 8 MB
+    peak.update()
+    synchronize(device)
+    assert peak.peak_mb >= 4.0
+    del buffer
+
+
+def test_synchronize_is_a_noop_on_cpu():
+    synchronize("cpu")  # 不应抛异常