vrr/prima.cpp
2
0
Fork 0
mirror of https://github.com/Lizonghang/prima.cpp.git synced 2025-09-07 08:59:03 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix display

Browse source
This commit is contained in:
Lizonghang 2024-12-08 22:57:12 +04:00
parent aad604ec8b
commit 2c2171cebf
1 changed files with 3 additions and 3 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

6
src/llama.cpp
View file

@ -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);
}
}