CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-31 08:51:55 +00:00
Code Issues Packages Projects Releases Wiki Activity

llama : do not print "offloading layers" message in CPU-only builds (#5416)

Browse Source
This commit is contained in:
slaren
2024-02-08 21:33:03 +01:00
committed by GitHub
parent 6e99f2a04f
commit 41f308f58e
1 changed files with 5 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
llama.cpp
View File

@@ -4209,8 +4209,7 @@ static bool llm_load_tensors(
ctx_bufs.emplace_back(ctx, buf);
}
// print memory requirements
{
if (llama_supports_gpu_offload()) {
const int n_gpu = std::min(n_gpu_layers, int(hparams.n_layer));
LLAMA_LOG_INFO("%s: offloading %d repeating layers to GPU\n", __func__, n_gpu);
@@ -4222,10 +4221,11 @@ static bool llm_load_tensors(
const int max_offloadable_layers = hparams.n_layer + 1;
LLAMA_LOG_INFO("%s: offloaded %d/%d layers to GPU\n", __func__, std::min(n_gpu_layers, max_offloadable_layers), max_backend_supported_layers);
}
for (ggml_backend_buffer_t buf : model.bufs) {
LLAMA_LOG_INFO("%s: %10s buffer size = %8.2f MiB\n", __func__, ggml_backend_buffer_name(buf), ggml_backend_buffer_get_size(buf) / 1024.0 / 1024.0);
}
// print memory requirements
for (ggml_backend_buffer_t buf : model.bufs) {
LLAMA_LOG_INFO("%s: %10s buffer size = %8.2f MiB\n", __func__, ggml_backend_buffer_name(buf), ggml_backend_buffer_get_size(buf) / 1024.0 / 1024.0);
}
// populate tensors_by_name