1 files changed, 3 insertions, 0 deletions
diff --git a/llama.h b/llama.h
index 0b2e708d..612e32c4 100644
--- a/llama.h
+++ b/llama.h
@@ -242,6 +242,9 @@ extern "C" {
         // proportion of the model (layers or rows) to offload to each GPU, size: llama_max_devices()
         const float * tensor_split;
 
+        // comma separated list of RPC servers to use for offloading
+        const char * rpc_servers;
+
         // Called with a progress value between 0.0 and 1.0. Pass NULL to disable.
         // If the provided progress_callback returns true, model loading continues.
         // If it returns false, model loading is immediately aborted.