Quantized GGUF style (#1523)

* 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).

* Cleanup.

* Fix the rebase.

* Removing the fences speeds everything up and *is* correct this time...

* Cleanup the fence.

* After rebase.

* Bad code removal.

* Rebase after phi2 merge + fix replit default to CPU.

* Making the CI happy.

* More happy tests.

---------

Co-authored-by: Nicolas Patry <nicolas@Nicolass-MacBook-Pro.local>
This commit is contained in:
Nicolas Patry
2024-01-17 10:27:58 +01:00
committed by GitHub
parent 5270224f40
commit 403680f17d
31 changed files with 6446 additions and 515 deletions

View File

@ -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.