llama.cpp/ggml.c at c5d70f5c9ea5a8f0f6b0d6aa741455978a1dabfd - llama.cpp - Gitea - Peisong Xiao

CS348Project/llama.cpp

mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-15 11:17:31 +00:00

Files

Howard Su c5d70f5c9e ggml : optimize rope function to avoid call powf in the tight loop (#807 )

2023-04-14 09:24:52 +03:00

337 KiB

Raw Blame History

View Raw