llama.cpp

cfb9d4b7 - mtmd: require an F32 position embedding for HunyuanVL (#32131)

mtmd: require an F32 position embedding for HunyuanVL (#32131) HunyuanVL resamples its position embedding on the host into a float buffer sized for F32, then reads ggml_nbytes() of the tensor into it. The graph never uses the tensor, so any type loads, and an F64 tensor overflows the buffer at the first image request. Require the position embedding to be present and F32 when loading the HunyuanVL tensors.