ver4a/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

llama : print size and type of overridden tensors (#13364)

Browse source
This commit is contained in:
Diego Devesa 2025-05-08 13:15:15 +02:00 • committed by GitHub
parent 8733e0cf6e
commit f061021206
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 4 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

5
src/llama-model.cpp
View file

@ -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;
}
}