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

llama : add thread safety test (#14035)

Browse source 
* llama : add thread safety test

* llamafile : remove global state

* llama : better LLAMA_SPLIT_MODE_NONE logic

when main_gpu < 0 GPU devices are not used

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
Diego Devesa 2025-06-16 08:11:43 -07:00 • committed by GitHub
parent 0dbcabde8c
commit 6adc3c3ebc
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
9 changed files with 192 additions and 18 deletions
Download patch file Download diff file Expand all files Collapse all files

18
src/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) {