mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2025-10-27 08:21:30 +00:00
a80ff183ab
This commit updates the leftover handling in ggml_vec_scale_f32. The motivation for this is that the code currently incorrectly assumes there would be fewer than ggml_f32_epr leftover elements. However, since the main loop processes 2*ggml_f32_epr elements per iteration , there can be up to (2*ggml_f32_epr - 1) leftover elements. The original single-pass leftover code could only process ggml_f32_epr elements, leaving some elements unscaled. Example scenario with 256-bit SVE: ``` ggml_f32_epr = 8 (elements per register) ggml_f32_step = 16 (two registers per iteration) n = 25 np = 16 leftovers = 9 elements (16-24) Original : processes only elements 16-23, misses element 24 This commit : loop processes elements 16-23, then element 24 ``` Refs: https://github.com/ggml-org/llama.cpp/actions/runs/18070620247/job/51419855630