module
encodings
Implementations of quantization encodings.
Aliases
-
QK_K = 256
: Size of superblock quantized elements, in bytes. -
K_SCALE_SIZE = 12
: Size of superblock scales and mins, in bytes.
Structs
-
BFloat16Encoding
: The bfloat16 quantization encoding. -
Float32Encoding
: The float32 quantization encoding. -
Q4_0Encoding
: The Q4_0 quantization encoding. -
Q4_KEncoding
: The Q4_K quantization encoding. -
Q6_KEncoding
: The Q6_K quantization encoding.