llama : extend API to get max devices at runtime (#2253)

ggerganov · Jul 19, 2023 · 294f424 · 294f424
1 parent 45a1b07
commit 294f424
Show file tree

Hide file tree

Showing 2 changed files with 6 additions and 0 deletions.
diff --git a/llama.cpp b/llama.cpp
@@ -875,6 +875,10 @@ struct llama_model_quantize_params llama_model_quantize_default_params() {
     return result;
 }
 
+int llama_max_devices() {
+    return LLAMA_MAX_DEVICES;
+}
+
 bool llama_mmap_supported() {
     return llama_mmap::SUPPORTED;
 }

diff --git a/llama.h b/llama.h
@@ -153,6 +153,8 @@ extern "C" {
         int32_t n_eval;
     };
 
+    LLAMA_API int llama_max_devices();
+
     LLAMA_API struct llama_context_params llama_context_default_params();
     LLAMA_API struct llama_model_quantize_params llama_model_quantize_default_params();