root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-24 10:24:35 +00:00
Code Issues Actions 5 Packages Projects Releases Wiki Activity

server : add KV cache quantization options (#5684)

Browse Source
This commit is contained in:
AlpinDale 2024-02-23 19:31:54 +00:00 committed by GitHub
parent 54fbcd2ce6
commit fd43d66f46
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 10 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
examples/server/server.cpp
View File

@ -1948,6 +1948,10 @@ static void server_print_usage(const char *argv0, const gpt_params &params,
printf(" -cb, --cont-batching enable continuous batching (a.k.a dynamic batching) (default: disabled)\n");
printf(" -spf FNAME, --system-prompt-file FNAME\n");
printf(" set a file to load a system prompt (initial prompt of all slots), this is useful for chat applications.\n");
printf(" -ctk TYPE, --cache-type-k TYPE\n");
printf(" KV cache data type for K (default: f16)\n");
printf(" -ctv TYPE, --cache-type-v TYPE\n");
printf(" KV cache data type for V (default: f16)\n");
printf(" --mmproj MMPROJ_FILE path to a multimodal projector file for LLaVA.\n");
printf(" --log-disable disables logging to a file.\n");
printf(" --slots-endpoint-disable disables slots monitoring endpoint.\n");
@ -2386,6 +2390,12 @@ static void server_params_parse(int argc, char **argv, server_params &sparams,
);
llama.process_system_prompt_data(json::parse(systm_content));
}
else if (arg == "-ctk" || arg == "--cache-type-k") {
params.cache_type_k = argv[++i];
}
else if (arg == "-ctv" || arg == "--cache-type-v") {
params.cache_type_v = argv[++i];
}
else if(arg == "--mmproj")
{
if (++i >= argc)