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

server : update /props with "total_slots" value (#5373)

Browse source 
* include total "num_slots" in default_generation_settings_for_props

* cleanup total_slots return value in /props endpoint

* update /props endpoint docs with total_slots

* remove num_slots from default_generation_settings_for_props

* update /props endpoint section
This commit is contained in:
Justin Parker 2024-02-07 01:15:19 -05:00 • committed by GitHub
parent f68664ac24
commit f3e2b4fa3f
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 5 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

4
examples/server/server.cpp
View file

@ -432,7 +432,6 @@ struct llama_server_context
}
default_generation_settings_for_props = get_formated_generation(slots.front());
default_generation_settings_for_props["num_slots"] = params.n_parallel;
default_generation_settings_for_props["seed"] = -1;
batch = llama_batch_init(n_ctx, 0, params.n_parallel);
@ -2639,7 +2638,8 @@ int main(int argc, char **argv)
json data = {
{ "user_name", llama.name_user.c_str() },
{ "assistant_name", llama.name_assistant.c_str() },
{ "default_generation_settings", llama.default_generation_settings_for_props }
{ "default_generation_settings", llama.default_generation_settings_for_props },
{ "total_slots", llama.params.n_parallel }
};
res.set_content(data.dump(), "application/json; charset=utf-8");
});