Skip to content

LLM inference in C/C++

C++ ggml

tests : remove unnecessary sync in test-save-load-state (#26166)

Georgi Gerganov7ef790f90a47
diff --git a/tests/test-save-load-state.cpp b/tests/test-save-load-state.cpp
index bbb025617f..6e93ce6fb8 100644
--- a/tests/test-save-load-state.cpp
+++ b/tests/test-save-load-state.cpp
@@ -44,8 +44,6 @@ static llama_tokens generate_tokens(llama_context * ctx, llama_sampler * smpl, i
n_past++;
}
- llama_synchronize(ctx);
-
return result;
}