ggml-org/llama.cpp b11854

on GitHub

vulkan: ggml src1 precision support (#30656)

• vulkan: update accumulator precision selection

• handle fp32 overflows through scaling

• handle overflows in copy-to-fp16 activations

• add missing cases

• simplify code

• add tests

• add ggml prec get helpers, use in Vulkan backend

• clean up comments

• revert comment edit

• trim tests

• also handle fp32 src0, fix test scaling src0 values too

• don't scale if disabled

• remove fp16 scaling

• add check to mul_mat

• fix inconsistency

• rename to acc_prec