Described in https://docs.nvidia.com/cuda/developer-preview/13.4/parallel-thread-execution/index.html#alternate-floating-point-data-formats. Seemingly a block-scale type for Rubin, leveraging the 8th bit that goes unused in the UE4M3 scale type of NVFP4.
The ue5m3 encoding does not support infinity. NaN value is limited to 0xff.
Trivially added with @microfloat Float8_E5M3FNU sign=0 exponent=5 significand=3 nonfinite=NanOnlyAllOnes, but also requires registration in the CUDA extension for it to be recognized by e.g. cuBLASLt.
Described in https://docs.nvidia.com/cuda/developer-preview/13.4/parallel-thread-execution/index.html#alternate-floating-point-data-formats. Seemingly a block-scale type for Rubin, leveraging the 8th bit that goes unused in the UE4M3 scale type of NVFP4.
The
ue5m3encoding does not support infinity.NaNvalue is limited to0xff.Trivially added with
@microfloat Float8_E5M3FNU sign=0 exponent=5 significand=3 nonfinite=NanOnlyAllOnes, but also requires registration in the CUDA extension for it to be recognized by e.g. cuBLASLt.