From 1ef41c2124ebfcd9ca3447f60e57ed287129486d Mon Sep 17 00:00:00 2001
From: Concedo <39025047+LostRuins@users.noreply.github.com>
Date: Thu, 13 Mar 2025 14:58:08 +0800
Subject: [PATCH] streamline output console log (+1 squashed commits)

Squashed commits:

[ca474bdd] streamline output console log
---
 examples/llava/clip.cpp | 5 +++++
 gpttype_adapter.cpp     | 9 ++++++++-
 2 files changed, 13 insertions(+), 1 deletion(-)

diff --git a/examples/llava/clip.cpp b/examples/llava/clip.cpp
index d8022edb4..82d71a314 100644
--- a/examples/llava/clip.cpp
+++ b/examples/llava/clip.cpp
@@ -3171,6 +3171,11 @@ bool clip_model_quantize(const char * fname_inp, const char * fname_out, const i
             {
                 quantize = false;
             }
+            // //temp fix for gemma3
+            // if(name.find("ffn_up.weight") != std::string::npos)
+            // {
+            //     quantize = false;
+            // }
         }
 
         if (quantize) {
diff --git a/gpttype_adapter.cpp b/gpttype_adapter.cpp
index fbfd59132..48ca9f32b 100644
--- a/gpttype_adapter.cpp
+++ b/gpttype_adapter.cpp
@@ -3993,7 +3993,14 @@ generation_outputs gpttype_generate(const generation_inputs inputs)
     float pt2 = (time2*1000.0/(realnpredict<=0?1:realnpredict));
     float ts2 = (1000.0/pt2);
     float tokens_per_second = (realnpredict <= 0 ? 0 : realnpredict / (time1 + time2));
-    printf("\n[%s] CtxLimit:%d/%d, Amt:%d/%d, Init:%.2fs, Process:%.2fs (%.1fms/T = %.2fT/s), Generate:%.2fs (%.1fms/T = %.2fT/s), Total:%.2fs (%.2fT/s)",get_timestamp_str().c_str(),(int)current_context_tokens.size(),(int)nctx, realnpredict, kcpp_data->n_predict, time0, time1, pt1, ts1, time2, pt2, ts2, (time1 + time2), tokens_per_second);
+    if(debugmode==1)
+    {
+        printf("\n[%s] CtxLimit:%d/%d, Amt:%d/%d, Init:%.2fs, Process:%.2fs (%.1fms/T = %.2fT/s), Generate:%.2fs (%.1fms/T = %.2fT/s), Total:%.2fs (%.2fT/s)",get_timestamp_str().c_str(),(int)current_context_tokens.size(),(int)nctx, realnpredict, kcpp_data->n_predict, time0, time1, pt1, ts1, time2, pt2, ts2, (time1 + time2), tokens_per_second);
+    }
+    else
+    {
+         printf("\n[%s] CtxLimit:%d/%d, Amt:%d/%d, Init:%.2fs, Process:%.2fs (%.2fT/s), Generate:%.2fs (%.2fT/s), Total:%.2fs",get_timestamp_str().c_str(),(int)current_context_tokens.size(),(int)nctx, realnpredict, kcpp_data->n_predict, time0, time1, ts1, time2, ts2, (time1 + time2));
+    }
     if(debugmode==1 && !is_quiet && (draft_successes+draft_failures)>0)
     {
         printf("\n(Draft Results - Success:%d, Failure:%d)",draft_successes,draft_failures);