Metal quantized modifications proposal.

- Add a device param, wherever needed.
- Create new QMetal storage thing that implements QuantizedType.
- Update everywhere needed.

Fix Python.

Fixing examples.

Fix: fmt + clippy + stub.

Moving everything around.

Only missing the actual implems.

Fixing everything + adding dequantized kernels.

More work.

Fixing matmul.

Fmt + Clippy

Some clippy fixes.

Working state.

Q2K Metal -> Bugged (also present in GGML).
Q4K CPU -> Bugged (present previously, new test catch it).
Q5K CPU -> Bugged (present previously).
Q8_1 Both -> Never really implemented it seems
Q8K metal -> Never implemented in metal

Fixing Q2K bug (present in ggml).

candle-pyo3/py_src/candle/utils/__init__.pyi

@@ -33,7 +33,9 @@ def has_mkl() -> bool:
     pass
 
 @staticmethod
-def load_ggml(path: Union[str, PathLike]) -> Tuple[Dict[str, QTensor], Dict[str, Any], List[str]]:
+def load_ggml(
+    path: Union[str, PathLike], device: Optional[Device] = None
+) -> Tuple[Dict[str, QTensor], Dict[str, Any], List[str]]:
     """
     Load a GGML file. Returns a tuple of three objects: a dictionary mapping tensor names to tensors,
     a dictionary mapping hyperparameter names to hyperparameter values, and a vocabulary.
@@ -41,7 +43,9 @@ def load_ggml(path: Union[str, PathLike]) -> Tuple[Dict[str, QTensor], Dict[str,
     pass
 
 @staticmethod
-def load_gguf(path: Union[str, PathLike]) -> Tuple[Dict[str, QTensor], Dict[str, Any]]:
+def load_gguf(
+    path: Union[str, PathLike], device: Optional[Device] = None
+) -> Tuple[Dict[str, QTensor], Dict[str, Any]]:
     """
     Loads a GGUF file. Returns a tuple of two dictionaries: the first maps tensor names to tensors,
     and the second maps metadata keys to metadata values.