ggml-org/llama.cpp b11761

on GitHub

ggml-cpu : select the NEON fp32->fp16 conversion (#30505)

The _ARM_NEON branch defines both GGML_CPU_COMPUTE* macros but selects
only FP16_TO_FP32, so FP32_TO_FP16 falls through to the portable
software conversion while neon_compute_fp32_to_fp16, a single fcvt,
stays defined and referenced by nothing. POWER9_VECTOR and
__riscv_zfhmin select both.

Add an #error pair that refuses a branch defining a COMPUTE macro
without selecting it. That is how this stayed unnoticed: the fallback
silently supplies a correct software implementation, so the only
symptom is a hardware instruction nothing ever reaches. The
FP16_TO_FP32 half carries a !defined(F16C) carve-out, because PR
30343 keeps that direction on the lookup table on purpose.

Replace the comment above the fallback: it singled out NEON and POWER9
and pointed at a selection that now happens in the branch itself.