From: Sutou Kouhei <redacted>
Date: Fri, 30 Aug 2024 18:08:10 +0000 (+0900)
Subject: llama : fix llama_split_mode enum values in main_gpu document (#9057)
X-Git-Tag: upstream/0.0.4488~840
X-Git-Url: https://git.djapps.eu/?a=commitdiff_plain;h=0ab30f8d82fc7156b750c194d64a887e80cbfb82;p=pkg%2Fggml%2Fsources%2Fllama.cpp

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 c3bda9e0..f2e70160 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()