ver4a/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

server : remove obsolete --memory-f32 option

Browse source
This commit is contained in:
Georgi Gerganov 2024-04-04 09:34:58 +03:00
parent 1a43c7254e
commit 4399f13fb9
No known key found for this signature in database
GPG key ID: BF970631944C16B7
2 changed files with 0 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

2
examples/server/server.cpp
View file

@ -2189,8 +2189,6 @@ static void server_print_usage(const char * argv0, const gpt_params & params, co
printf(" KV cache defragmentation threshold (default: %.1f, < 0 - disabled)\n", params.defrag_thold);
printf(" -b N, --batch-size N logical maximum batch size (default: %d)\n", params.n_batch);
printf(" -ub N, --ubatch-size N physical maximum batch size (default: %d)\n", params.n_ubatch);
printf(" --memory-f32 use f32 instead of f16 for memory key+value (default: disabled)\n");
printf(" not recommended: doubles context memory required and no measurable increase in quality\n");
if (llama_supports_mlock()) {
printf(" --mlock force system to keep model in RAM rather than swapping or compressing\n");
}