llama.cpp/ggml-quants.c at b96f9afb0d58b003ac8d1d0c94cd99393a3bc437

mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-01 09:01:57 +00:00

Files

Hong Bo PENG b5fcf8ef5c ggml : fix and optimize ppc64le (ggml/849)

* fix compile issues introduced by loongarch_asx

* restore quant changes to merge

* fix compile issues introduced by loongarch_asx

* further optimize by using vec_msum & vec_sum4s on ppc64le

2024-06-16 20:32:49 +03:00

600 KiB

Raw Blame History

View Raw

600 KiB Raw Blame History

600 KiB

Raw Blame History