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

Revert "Support using mmap when applying LoRA (#2095)" (#2206)

Browse source 
Has perf regression when mlock is used.

This reverts commit 2347463201.
This commit is contained in:
Howard Su 2023-07-13 21:58:25 +08:00 • committed by GitHub
parent ff5d58faec
commit 32c5411631
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
5 changed files with 9 additions and 7 deletions
Download patch file Download diff file Expand all files Collapse all files

3
examples/server/server.cpp
View file

@ -632,7 +632,7 @@ static void server_print_usage(const char *argv0, const gpt_params &params,
fprintf(stderr, " model path (default: %s)\n", params.model.c_str());
fprintf(stderr, " -a ALIAS, --alias ALIAS\n");
fprintf(stderr, " set an alias for the model, will be added as `model` field in completion response\n");
fprintf(stderr, " --lora FNAME apply LoRA adapter\n");
fprintf(stderr, " --lora FNAME apply LoRA adapter (implies --no-mmap)\n");
fprintf(stderr, " --lora-base FNAME optional model to use as a base for the layers modified by the LoRA adapter\n");
fprintf(stderr, " --host ip address to listen (default (default: %s)\n", sparams.hostname.c_str());
fprintf(stderr, " --port PORT port to listen (default (default: %d)\n", sparams.port);
@ -820,6 +820,7 @@ static void server_params_parse(int argc, char **argv, server_params &sparams,
break;
}
params.lora_adapter = argv[i];
params.use_mmap = false;
}
else if (arg == "--lora-base")
{