diff options
| author | Georgi Gerganov <ggerganov@gmail.com> | 2024-05-23 10:00:21 +0300 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2024-05-23 10:00:21 +0300 |
| commit | e84b71c2c6da6e69c8f815168ea836f9716a325e (patch) | |
| tree | aa5c046cc5f0e9e953de5329412a753d82e60589 /gguf-py | |
| parent | 1b1e27cb49158123ef4902aa41eb368c9e76e6a1 (diff) | |
ggml : drop support for QK_K=64 (#7473)
* ggml : drop support for QK_K=64
ggml-ci
* opencl : restore QK_K=256 define
Diffstat (limited to 'gguf-py')
| -rw-r--r-- | gguf-py/gguf/constants.py | 3 |
1 files changed, 1 insertions, 2 deletions
diff --git a/gguf-py/gguf/constants.py b/gguf-py/gguf/constants.py index 42df2e4d..67e23dcc 100644 --- a/gguf-py/gguf/constants.py +++ b/gguf-py/gguf/constants.py @@ -905,9 +905,8 @@ class GGUFValueType(IntEnum): raise ValueError(f"Unknown type: {type(val)}") -# Note: Does not support GGML_QKK_64 -QK_K = 256 # Items here are (block size, type size) +QK_K = 256 GGML_QUANT_SIZES: dict[GGMLQuantizationType, tuple[int, int]] = { GGMLQuantizationType.F32: (1, 4), GGMLQuantizationType.F16: (1, 2), |