From 2c2171cebf99481420f581cb3b90c31aff787ae8 Mon Sep 17 00:00:00 2001 From: Lizonghang <870644199@qq.com> Date: Sun, 8 Dec 2024 22:57:12 +0400 Subject: [PATCH] fix display --- src/llama.cpp | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/src/llama.cpp b/src/llama.cpp index 1696cd07..c021541e 100644 --- a/src/llama.cpp +++ b/src/llama.cpp @@ -3884,7 +3884,7 @@ static bool llama_kv_cache_init( return false; } ggml_backend_buffer_clear(buf, 0); - LLAMA_LOG_INFO("%s: %10s KV buffer size = %8.2f MiB\n", __func__, ggml_backend_buffer_name(buf), ggml_backend_buffer_get_size(buf)/1024.0/1024.0); + LLAMA_LOG_INFO("%s: %11s KV buffer size = %8.2f MiB\n", __func__, ggml_backend_buffer_name(buf), ggml_backend_buffer_get_size(buf)/1024.0/1024.0); cache.bufs.push_back(buf); } @@ -7373,10 +7373,10 @@ static bool llm_load_tensors_impl( GGML_ASSERT(local_i != -1); if (local_i % window_size >= window_size - n_gpu_layers) { - LLAMA_LOG_INFO("Layer %i assigned to gpu (cache index %i)\n", i, local_i); + // LLAMA_LOG_INFO("Layer %i assigned to gpu (cache index %i)\n", i, local_i); model.buft_layer[local_i] = llama_default_buffer_type_offload(model, main_gpu); } else { - LLAMA_LOG_INFO("Layer %i assigned to cpu (cache index %i)\n", i, local_i); + // LLAMA_LOG_INFO("Layer %i assigned to cpu (cache index %i)\n", i, local_i); model.buft_layer[local_i] = llama_default_buffer_type_cpu(model, true); } }