notes

commit 29303f4b4f060ac3b450731965a04be3e53c9212
parent 10861dec9b980519d83e98d74f004e3e4e2d42a9
Author: ling0x <ling0x@users.noreply.github.com>
Date:   Sat, 27 Jun 2026 16:21:32 +0100

commands

Diffstat:
M
commands/llama-cpp.txt
 | 
14
++++++++++++++

1 file changed, 14 insertions(+), 0 deletions(-)
diff --git a/commands/llama-cpp.txt b/commands/llama-cpp.txt
@@ -11,6 +11,20 @@ Optimizations:
 ====================================================================
 Commands:
 
+git clone git@github.com:ggml-org/llama.cpp.git
+
+cd llama.cpp
+
+Build with CUDA:
+
+cmake -B build -DGGML_CUDA=ON
+cmake --build build --config Release
+
+Build CPU:
+
+cmake -B build
+cmake --build build --config Release
+
 Run on NVIDIA GPU without reasoning:
 
 ./build/bin/llama-server -hf unsloth/gemma-4-12b-it-GGUF -ngl 999 -c 32768 --host 0.0.0.0 --port 9090 --reasoning off