Microscaling

Documentation for Microscaling.

Microscaling.MXFP4Type
MXFP4

MXFP4 is a microscaling format using FP4 elements (E2M1, no NaN/Inf), with E8M0 scale factors, each scaling contiguous element blocks of 32.

source
Microscaling.MXFP6_E2M3Type
MXFP6_E2M3

MXFP6_E2M3 is a microscaling format using FP6 elements (E2M3, no NaN/Inf), with E8M0 scale factors, each scaling contiguous element blocks of 32.

source
Microscaling.MXFP6_E3M2Type
MXFP6_E3M2

MXFP6_E3M2 is a microscaling format using FP6 elements (E3M2, no NaN/Inf), with E8M0 scale factors, each scaling contiguous element blocks of 32.

source
Microscaling.MXFP8_E4M3Type
MXFP8_E4M3

MXFP8_E4M3 is a microscaling format using FP8 elements (E4M3, including NaN), with E8M0 scale factors, each scaling contiguous element blocks of 32.

source
Microscaling.MXFP8_E5M2Type
MXFP8_E5M2

MXFP8_E5M2 is a microscaling format using FP8 elements (E5M2, including NaN/Inf), with E8M0 scale factors, each scaling contiguous element blocks of 32.

source
Microscaling.MXINT8Type
MXINT8

MXINT8 is a microscaling format using INT8 elements (Int8, scaled down by 64), with E8M0 scale factors, each scaling contiguous element blocks of 32.

source
Microscaling.NVFP4Type
NVFP4

NVFP4 is a microscaling format using FP4 elements (E2M1, no NaN/Inf), with E4M3 scale factors, each scaling contiguous element blocks of 16.

source