fix tools (+3 squashed commit)

Squashed commit:

[95a489ee] fix tools build

[1d3d3451] add accelerate

[2837705c] edit a line

.github/workflows/kcpp-build-release-win-full-cu12.yaml

@@ -88,7 +88,7 @@ jobs:
       - name: Generate VK Instructions
         id: gen_vk_instructions
         run: |
-          echo "If you cannot compile vulkan shaders yourself with glslc, you can manually patch in precompiled vulkan shader source files. Copy these 2 files to the ggml/src directory before building." > vulkan-readme.txt
+          echo "If you cannot compile vulkan shaders yourself with glslc, you can manually patch in precompiled vulkan shader source files. Copy ggml-vulkan-shaders.cpp and ggml-vulkan-shaders.hpp to the ggml/src subdirectory in KoboldCpp source files before building." > vulkan-readme.txt
 
       - name: Save Standalone Vulkan Shaders
         uses: actions/upload-artifact@v4

examples/gguf-split/gguf-split.cpp

@@ -1,7 +1,7 @@
 #include "ggml.h"
 #include "gguf.h"
 #include "llama.h"
-#include "common.h"
+#include "common/common.h"
 #include "build-info.h"
 
 #include <algorithm>

examples/outetts/readme.md

@@ -16,7 +16,7 @@ You can also create your own cloned speaker voice.
 To do that, you will need Python 3.10+ with the `outetts` package installed. You can install it with this commands:
 ```
 pip install outetts --no-deps
-pip install scipy einops pyyaml huggingface-hub encodec matplotlib transformers pytorch-lightning tensorboardX soundfile numpy jsonargparse torchcrepe librosa inflect loguru polars natsort tqdm sounddevice mecab-python3 unidic-lite uroman openai-whisper pygame
+pip install scipy einops pyyaml huggingface-hub encodec matplotlib transformers pytorch-lightning tensorboardX soundfile numpy jsonargparse torchcrepe librosa inflect loguru polars natsort tqdm sounddevice mecab-python3 unidic-lite uroman openai-whisper pygame accelerate
 ```
 Then after that, obtain a wav file containing a sample of the voice you want to clone.
 Modify the [voice_cloning.py](voice_cloning.py) script with your input audio file, and let it generate the JSON.

examples/quantize/quantize.cpp

@@ -1,5 +1,5 @@
 #include "build-info.h"
-#include "common.h"
+#include "common/common.h"
 #include "llama.h"
 
 #include <cstdio>