From 6dcc42bd6bf8d6fa7fc91e673a58c13489385ac5 Mon Sep 17 00:00:00 2001 From: slaren Date: Thu, 11 Jan 2024 03:28:07 +0100 Subject: [PATCH] fix whitespace --- llama.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/llama.h b/llama.h index d387ad77b..2d8ed371b 100644 --- a/llama.h +++ b/llama.h @@ -185,12 +185,13 @@ extern "C" { struct llama_model_params { int32_t n_gpu_layers; // number of layers to store in VRAM 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 int32_t main_gpu; + // proportion of the model (layers or rows) to offload to each GPU, size: LLAMA_MAX_DEVICES const float * tensor_split;