tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-27 20:05:20 +00:00
Code Issues Packages Projects Releases Wiki Activity

server : add --numa support (#2524)

Browse Source
This commit is contained in:
Cheng Shao
2023-08-14 15:36:42 +02:00
committed by GitHub
parent 348acf188c
commit d75561df20
2 changed files with 6 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
examples/server/server.cpp
View File

@ -666,6 +666,7 @@ static void server_print_usage(const char *argv0, const gpt_params &params,
{
fprintf(stdout, " --no-mmap do not memory-map model (slower load but may reduce pageouts if not using mlock)\n");
}
fprintf(stdout, " --numa attempt optimizations that help on some NUMA systems\n");
#ifdef LLAMA_SUPPORTS_GPU_OFFLOAD
fprintf(stdout, " -ngl N, --n-gpu-layers N\n");
fprintf(stdout, " number of layers to store in VRAM\n");
@ -940,6 +941,10 @@ static void server_params_parse(int argc, char **argv, server_params &sparams,
{
params.use_mmap = false;
}
else if (arg == "--numa")
{
params.numa = true;
}
else if (arg == "--embedding")
{
params.embedding = true;