MCPcopy Create free account
hub / github.com/InfiniTensor/InfiniTensor / fill_fp16

Method fill_fp16

include/utils/data_generator.h:46–51  ·  view source on GitHub ↗

FIXME: fix the accuracy standards when dtype is float16

Source from the content-addressed store, hash-verified

source not stored for this graph (policy: none)

Callers

nothing calls this directly

Calls 1

float_to_fp16Function · 0.85

Tested by

no test coverage detected