Microscaling
Documentation for Microscaling.
Microscaling.BlockFormatMicroscaling.MXFP4Microscaling.MXFP6_E2M3Microscaling.MXFP6_E3M2Microscaling.MXFP8_E4M3Microscaling.MXFP8_E5M2Microscaling.MXINT8Microscaling.NVFP4
Microscaling.BlockFormat — TypeBlockFormat{E,S,k}A block format specifies the element type, scale type, and number of elements per block.
Microscaling.MXFP4 — TypeMXFP4MXFP4 is a microscaling format using FP4 elements (E2M1, no NaN/Inf), with E8M0 scale factors, each scaling contiguous element blocks of 32.
Microscaling.MXFP6_E2M3 — TypeMXFP6_E2M3MXFP6_E2M3 is a microscaling format using FP6 elements (E2M3, no NaN/Inf), with E8M0 scale factors, each scaling contiguous element blocks of 32.
Microscaling.MXFP6_E3M2 — TypeMXFP6_E3M2MXFP6_E3M2 is a microscaling format using FP6 elements (E3M2, no NaN/Inf), with E8M0 scale factors, each scaling contiguous element blocks of 32.
Microscaling.MXFP8_E4M3 — TypeMXFP8_E4M3MXFP8_E4M3 is a microscaling format using FP8 elements (E4M3, including NaN), with E8M0 scale factors, each scaling contiguous element blocks of 32.
Microscaling.MXFP8_E5M2 — TypeMXFP8_E5M2MXFP8_E5M2 is a microscaling format using FP8 elements (E5M2, including NaN/Inf), with E8M0 scale factors, each scaling contiguous element blocks of 32.
Microscaling.MXINT8 — TypeMXINT8MXINT8 is a microscaling format using INT8 elements (Int8, scaled down by 64), with E8M0 scale factors, each scaling contiguous element blocks of 32.
Microscaling.NVFP4 — TypeNVFP4NVFP4 is a microscaling format using FP4 elements (E2M1, no NaN/Inf), with E4M3 scale factors, each scaling contiguous element blocks of 16.