From 0ab30f8d82fc7156b750c194d64a887e80cbfb82 Mon Sep 17 00:00:00 2001 From: Sutou Kouhei Date: Sat, 31 Aug 2024 03:08:10 +0900 Subject: [PATCH] llama : fix llama_split_mode enum values in main_gpu document (#9057) LLAMA_SPLIT_* were renamed to LLAMA_SPLIT_MODE_* in #5697. --- include/llama.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/include/llama.h b/include/llama.h index c3bda9e02..f2e701602 100644 --- 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()