llama.cpp/common/arg.cpp at 017f10b5fa630a013ec4f9936e410a60d4f460d5 - 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

David Huang 7f323a589f Add --no-op-offload to improve -ot pp perf in MoE models like llama4 400B (#13386 )

2025-05-11 14:18:39 +02:00

140 KiB

Raw Blame History

View Raw