llama.cpp/ggml-cuda.cu at 800f4fe48eba1f36c0aba66a5a28521ab38f971d - llama.cpp - Gitea - Peisong Xiao

CS348Project/llama.cpp

mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-02 09:12:03 +00:00

Files

Alan Gray 800f4fe48e Tidied to now only use CUDA runtime (not mixed with driver calls)

2024-04-22 05:11:05 -07:00

110 KiB

Raw Blame History

View Raw