From: Equim <redacted>
Date: Fri, 11 Aug 2023 22:35:14 +0000 (+0800)
Subject: server: fixed wrong variable name in timing json (#2579)
X-Git-Tag: gguf-v0.4.0~330
X-Git-Url: https://git.djapps.eu/?a=commitdiff_plain;h=53dc399472d5bd35ee739b865e843b1996bd3814;p=pkg%2Fggml%2Fsources%2Fllama.cpp

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

* server: fixed wrong variable name in timing json

* remove redunct entry
---

diff --git a/examples/server/server.cpp b/examples/server/server.cpp
index 637f6d6c..2340f93a 100644
--- a/examples/server/server.cpp
+++ b/examples/server/server.cpp
@@ -1008,7 +1008,7 @@ static json format_timings(llama_server_context &llama)
     assert(timings.n_eval == llama.num_tokens_predicted);
 
     return json{
-        {"prompt_n", timings.n_eval},
+        {"prompt_n", timings.n_p_eval},
         {"prompt_ms", timings.t_p_eval_ms},
         {"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},
@@ -1037,7 +1037,6 @@ static json format_final_response(llama_server_context &llama, const std::string
         {"stopped_limit", llama.stopped_limit},
         {"stopping_word", llama.stopping_word},
         {"tokens_cached", llama.n_past},
-        {"tokens_predicted", llama.num_tokens_predicted},
         {"timings", format_timings(llama)},
     };