vrr/prima.cpp
2
0
Fork 0
mirror of https://github.com/Lizonghang/prima.cpp.git synced 2025-09-09 14:24:37 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

reduce kv cache from available memory

Browse source
This commit is contained in:
Lizonghang 2024-11-28 20:21:21 +04:00
parent 9858d90ce4
commit 45a1e55eec
5 changed files with 25 additions and 7 deletions
Download patch file Download diff file Expand all files Collapse all files

2
common/common.cpp
View file

@ -914,7 +914,7 @@ struct llama_init_result llama_init_from_gpt_params(gpt_params & params) {
dev_info_set = (struct device_info *)malloc(n_world * sizeof(struct device_info));
dev_info_set[0] = dev_info;
llama_gather_device_info(lctx, dev_info_set);
device_print_props(dev_info_set, n_world, model);
device_print_props(dev_info_set, n_world, model, cparams);
} else {
llama_send_device_info(lctx, &dev_info);
}