llama.cpp/ggml.c at 4caebf6d408b91c2d29d0abc7b1e867b5de64db5 - llama.cpp - Gitea - Peisong Xiao

CS348Project/llama.cpp

mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-31 08:51:55 +00:00

Files

Georgi Gerganov dcdd65e296 ggml : optimize ggml_vec_dot_q4_0_q8_0() using vectorized accumulators

2023-04-18 22:59:17 +03:00

373 KiB

Raw Blame History

View Raw