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

test-thread-safety : handle tiny training context of the input model

Browse Source
This commit is contained in:
Georgi Gerganov
2025-10-28 12:49:10 +02:00
parent 8e11ec8eee
commit ac261bea66
1 changed files with 8 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
tests/test-thread-safety.cpp
View File

@@ -131,7 +131,14 @@ int main(int argc, char ** argv) {
} }
batch = llama_batch_get_one(&token, 1); batch = llama_batch_get_one(&token, 1);
if (llama_decode(ctx.get(), batch)) {
int ret = llama_decode(ctx.get(), batch);
if (ret == 1 && i > 0) {
LOG_INF("Context full, stopping generation.\n");
break;
}
if (ret != 0) {
LOG_ERR("Model %d/%d, Context %d/%d: failed to decode\n", m + 1, num_models, c + 1, num_contexts); LOG_ERR("Model %d/%d, Context %d/%d: failed to decode\n", m + 1, num_models, c + 1, num_contexts);
failed.store(true); failed.store(true);
return; return;