Skip to content

LLM inference in C/C++

C++ ggml

llama : use int32_t for llama_sampler_chain_n return type (#28631)

linsen458-spec4850c7727fa7
diff --git a/include/llama.h b/include/llama.h
index ef7a012c43..3ab935939c 100644
--- a/include/llama.h
+++ b/include/llama.h
@@ -1357,7 +1357,7 @@ extern "C" {
LLAMA_API struct llama_sampler * llama_sampler_chain_get( struct llama_sampler * chain, int32_t i);
// the total number of samplers in the chain
- LLAMA_API int llama_sampler_chain_n (const struct llama_sampler * chain);
+ LLAMA_API int32_t llama_sampler_chain_n (const struct llama_sampler * chain);
// after removing a sampler, the chain will no longer own it, and it will not be freed when the chain is freed
LLAMA_API struct llama_sampler * llama_sampler_chain_remove( struct llama_sampler * chain, int32_t i);
diff --git a/src/llama-sampler.cpp b/src/llama-sampler.cpp
index 34a7988262..61d28ad8a8 100644
--- a/src/llama-sampler.cpp
+++ b/src/llama-sampler.cpp
@@ -1006,7 +1006,7 @@ struct llama_sampler * llama_sampler_chain_remove(struct llama_sampler * chain,
return result;
}
-int llama_sampler_chain_n(const struct llama_sampler * chain) {
+int32_t llama_sampler_chain_n(const struct llama_sampler * chain) {
const auto * p = (const llama_sampler_chain *) chain->ctx;
return p->samplers.size();