llama.cpp/ggml-quants.c at fa8a809a9119411bc9c3f00026550d0343f4d9b7 - llama.cpp - Gitea - Peisong Xiao

CS348Project/llama.cpp

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

Files

Georgi Gerganov 8380ecfb21 ggml : fix unnecessary f32 -> f16 -> f32 casts (mmla) (#5951 )

2024-03-09 17:36:20 +02:00

473 KiB

Raw Blame History

View Raw