happyz
/
llama.cpp
mirror of https://github.com/ggerganov/llama.cpp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

STYLE: clang-format

This commit is contained in:
Yu, Zijun 2025-05-09 13:07:27 +08:00 committed by Mustafa Cavus
parent a0b30529bf
commit f15a2cc057
1 changed files with 0 additions and 30 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

30
ggml/src/ggml-openvino/README.md
View File

@ -1,30 +0,0 @@
# Instructions to Modify and Build ggml with OpenVINO
## Step 1: Modify the Source Code
In order to change the frontend `.so` path to the path to `.so` file, you need to add path to the `.so` file in cmake compiler option:
1. Open a terminal and navigate to the root directory of this repo.
2. Run the following commands to configure:
```sh
mkdir build
cmake -B build -DGGML_OV_FRONTEND="${openvino_repo_dir}/bin/intel64/Release/libopenvino_ggml_frontend.so"
```
Where GGML_OV_FRONTEND should point to the path to `libopenvino_ggml_frontend.so` file.
## Step 2: Build the Project
After modifying the source code, you need to build the project using CMake. Follow these steps:
1. (Optional) Enable debug option for ggml-openvino, this will output dump of subgraph sent to OpenVINO, information after convert ggml_cgraph to GraphIterator, and calculation input value/output value of each OP:
```sh
cmake -B build -DGGML_OPENVINO_DEBUG=ON
```
2. Run the following commands to configure and build the project:
```sh
cmake -B build -DGGML_OPENVINO=ON
cmake --build build -j
```
This will configure the project with OpenVINO support and build it using multiple cores for faster compilation.