extern/whisper.cpp
1
0
Fork 1
mirror of https://github.com/ggerganov/whisper.cpp.git synced 2025-08-09 06:55:32 +02:00
Code Issues Packages Projects Releases Wiki Activity

talk-llama : sync llama.cpp

Browse Source 
ggml-ci
This commit is contained in:
Georgi Gerganov
2025-06-18 10:22:47 +03:00
parent 69061e356f
commit 2f60ebc3c2
26 changed files with 1454 additions and 504 deletions
Download Patch File Download Diff File Expand all files Collapse all files

18
examples/talk-llama/llama.cpp
View File

@ -198,14 +198,18 @@ static struct llama_model * llama_model_load_from_file_impl(
// if using single GPU mode, remove all except the main GPU
if (params.split_mode == LLAMA_SPLIT_MODE_NONE) {
if (params.main_gpu < 0 || params.main_gpu >= (int)model->devices.size()) {
LLAMA_LOG_ERROR("%s: invalid value for main_gpu: %d (available devices: %d)\n", __func__, params.main_gpu, (int)model->devices.size());
llama_model_free(model);
return nullptr;
if (params.main_gpu < 0) {
model->devices.clear();
} else {
if (params.main_gpu >= (int)model->devices.size()) {
LLAMA_LOG_ERROR("%s: invalid value for main_gpu: %d (available devices: %zu)\n", __func__, params.main_gpu, model->devices.size());
llama_model_free(model);
return nullptr;
}
ggml_backend_dev_t main_gpu = model->devices[params.main_gpu];
model->devices.clear();
model->devices.push_back(main_gpu);
}
ggml_backend_dev_t main_gpu = model->devices[params.main_gpu];
model->devices.clear();
model->devices.push_back(main_gpu);
}
for (auto * dev : model->devices) {