logs : reduce (llama/23021)

* logs : reduce

* args : fix envs

* server : fix build

* common : print verbosity level at start

* server : clean-up logs

* server : print prompt processing timings + sampling params

* minor : whitespaces

diff --git a/ggml/src/ggml-metal/ggml-metal-device.m b/ggml/src/ggml-metal/ggml-metal-device.m
index fab7891c00880bdcad7a5e0099f669583078ffd9..780dfe81bb3c15862ef3de3eb961369c320f0492 100644 (file)
--- a/ggml/src/ggml-metal/ggml-metal-device.m
+++ b/ggml/src/ggml-metal/ggml-metal-device.m
@@ -672,7 +672,7 @@ ggml_metal_device_t ggml_metal_device_init(int device) {
                 ![[dev->mtl_device name] containsString:@"M6"] &&
                 ![[dev->mtl_device name] containsString:@"A19"] &&
                 ![[dev->mtl_device name] containsString:@"A20"]) {
-                GGML_LOG_WARN("%s: tensor API disabled for pre-M5 and pre-A19 devices\n", __func__);
+                GGML_LOG_INFO("%s: tensor API disabled for pre-M5 and pre-A19 devices\n", __func__);
                 dev->props.has_tensor = false;
             }