From: 2114L3 <redacted>
Date: Tue, 16 Dec 2025 10:50:43 +0000 (+1000)
Subject: server: Update README.md incorrect argument (#18073)
X-Git-Tag: upstream/0.0.7446~16
X-Git-Url: https://git.djapps.eu/?a=commitdiff_plain;h=5f5f9b46376ac14d7f95b0d968c182f522602880;p=pkg%2Fggml%2Fsources%2Fllama.cpp

server: Update README.md incorrect argument (#18073)

n-gpu-layer is incorrect
argument is n-gpu-layers with the 's'
---

diff --git a/tools/server/README.md b/tools/server/README.md
index 073bcd2c..ef4990fa 100644
--- a/tools/server/README.md
+++ b/tools/server/README.md
@@ -1430,7 +1430,7 @@ Model presets allow advanced users to define custom configurations using an `.in
 llama-server --models-preset ./my-models.ini
 ```
 
-Each section in the file defines a new preset. Keys within a section correspond to command-line arguments (without leading dashes). For example, the argument `--n-gpu-layer 123` is written as `n-gpu-layer = 123`.
+Each section in the file defines a new preset. Keys within a section correspond to command-line arguments (without leading dashes). For example, the argument `--n-gpu-layers 123` is written as `n-gpu-layers = 123`.
 
 Short argument forms (e.g., `c`, `ngl`) and environment variable names (e.g., `LLAMA_ARG_N_GPU_LAYERS`) are also supported as keys.
 
@@ -1445,7 +1445,7 @@ version = 1
 ; string value
 chat-template = chatml
 ; numeric value
-n-gpu-layer = 123
+n-gpu-layers = 123
 ; flag value (for certain flags, you need to use the "no-" prefix for negation)
 jinja = true
 ; shorthand argument (for example, context size)