llama : fix llama_split_mode enum values in main_gpu document (#9057)

LLAMA_SPLIT_* were renamed to LLAMA_SPLIT_MODE_* in #5697.

diff --git a/include/llama.h b/include/llama.h
index c3bda9e02bb2163ea0a2c06132da2d4cbbc7e0cd..f2e701602bb00defb493560b7332aab74d0f8504 100644 (file)
--- a/include/llama.h
+++ b/include/llama.h
@@ -267,9 +267,9 @@ extern "C" {
         enum llama_split_mode split_mode; // how to split the model across multiple GPUs
 
         // main_gpu interpretation depends on split_mode:
-        // LLAMA_SPLIT_NONE: the GPU that is used for the entire model
-        // LLAMA_SPLIT_ROW: the GPU that is used for small tensors and intermediate results
-        // LLAMA_SPLIT_LAYER: ignored
+        // LLAMA_SPLIT_MODE_NONE: the GPU that is used for the entire model
+        // LLAMA_SPLIT_MODE_ROW: the GPU that is used for small tensors and intermediate results
+        // LLAMA_SPLIT_MODE_LAYER: ignored
         int32_t main_gpu;
 
         // proportion of the model (layers or rows) to offload to each GPU, size: llama_max_devices()