pub fn dequant_f16(src: &[u8]) -> Result<Vec<f32>, QuantError>Expand description
F16 (IEEE-754 binary16) widened to f32. Like dequant_bf16 this is
a plain element type, not a block format: every f16 value is exactly
representable in f32, so the widening is lossless. GgmlType::F16 is
what llama-quantize --pure-free conversions and every *-f16.gguf
carry, and it is also the dtype ggml uses for token_embd in some
mixed checkpoints.