From b2fb63cffd90351680a8cf48224afa43f1026280 Mon Sep 17 00:00:00 2001 From: slaren Date: Wed, 7 May 2025 21:12:34 +0200 Subject: [PATCH] llama : print size and type of overridden tensors --- src/llama-model.cpp | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/src/llama-model.cpp b/src/llama-model.cpp index 7b66e2a03e38e..1603eae1292c9 100644 --- a/src/llama-model.cpp +++ b/src/llama-model.cpp @@ -1651,8 +1651,11 @@ bool llama_model::load_tensors(llama_model_loader & ml) { for (const auto * overrides = ml.tensor_buft_overrides; overrides->pattern != nullptr; ++overrides) { std::regex pattern(overrides->pattern); if (std::regex_search(tensor_name, pattern)) { - LLAMA_LOG_DEBUG("tensor %s buffer type overriden to %s\n", tensor_name.c_str(), ggml_backend_buft_name(overrides->buft)); buft = overrides->buft; + LLAMA_LOG_DEBUG("tensor %s (%zu MiB %s) buffer type overridden to %s\n", + tensor_name.c_str(), + ggml_nbytes(t_meta) / 1024 / 1024, ggml_type_name(t_meta->type), + ggml_backend_buft_name(buft)); break; } }