mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2025-11-01 09:01:57 +00:00
export llama_timings as struct and expose them in server
This commit is contained in:
@@ -72,6 +72,9 @@ export async function* llama(prompt, params = {}, config = {}) {
|
||||
|
||||
// if we got a stop token from server, we will break here
|
||||
if (result.data.stop) {
|
||||
if (result.data.generation_settings) {
|
||||
generation_settings = result.data.generation_settings;
|
||||
}
|
||||
break;
|
||||
}
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user