CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-03 09:22:01 +00:00
Code Issues Packages Projects Releases Wiki Activity

server: fixed wrong variable name in timing json (#2579)

Browse Source 
* server: fixed wrong variable name in timing json

* remove redunct entry
This commit is contained in:
Equim
2023-08-12 06:35:14 +08:00
committed by GitHub
parent 9ca4abed89
commit 53dc399472
1 changed files with 1 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
examples/server/server.cpp
View File

@@ -1008,7 +1008,7 @@ static json format_timings(llama_server_context &llama)
assert(timings.n_eval == llama.num_tokens_predicted); assert(timings.n_eval == llama.num_tokens_predicted);
return json{ return json{
{"prompt_n", timings.n_eval}, {"prompt_n", timings.n_p_eval},
{"prompt_ms", timings.t_p_eval_ms}, {"prompt_ms", timings.t_p_eval_ms},
{"prompt_per_token_ms", timings.t_p_eval_ms / timings.n_p_eval}, {"prompt_per_token_ms", timings.t_p_eval_ms / timings.n_p_eval},
{"prompt_per_second", 1e3 / timings.t_p_eval_ms * timings.n_p_eval}, {"prompt_per_second", 1e3 / timings.t_p_eval_ms * timings.n_p_eval},
@@ -1037,7 +1037,6 @@ static json format_final_response(llama_server_context &llama, const std::string
{"stopped_limit", llama.stopped_limit}, {"stopped_limit", llama.stopped_limit},
{"stopping_word", llama.stopping_word}, {"stopping_word", llama.stopping_word},
{"tokens_cached", llama.n_past}, {"tokens_cached", llama.n_past},
{"tokens_predicted", llama.num_tokens_predicted},
{"timings", format_timings(llama)}, {"timings", format_timings(llama)},
}; };