ayo/ipex-llm
1
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 1

Small fix in llama.cpp troubleshooting guide (#12457)

Browse source
This commit is contained in:
Yuwen Hu 2024-11-27 19:22:11 +08:00 committed by GitHub
parent 6f3441ba4c
commit a2272b70d3
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 4 additions and 4 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

4
docs/mddocs/Quickstart/llama_cpp_quickstart.md
View file

@ -352,8 +352,8 @@ If you meet `System Error: sycl7.dll not found` on Windows or you meet similar e
1. if you have installed conda and if you are in the right conda environment which has pip installed oneapi dependencies on Windows 1. if you have installed conda and if you are in the right conda environment which has pip installed oneapi dependencies on Windows
2. if you have executed `source /opt/intel/oneapi/setvars.sh` on Linux 2. if you have executed `source /opt/intel/oneapi/setvars.sh` on Linux
#### 11. Check driver first when you meet garbage output #### 11. Check driver first when you meet garbage output on Windows
If you meet garbage output, please check if your GPU driver version is >= [31.0.101.5522](https://www.intel.cn/content/www/cn/zh/download/785597/823163/intel-arc-iris-xe-graphics-windows.html). If not, please follow the instructions in [this section](./install_linux_gpu.md#install-gpu-driver) to update your GPU driver. If you meet garbage output on Windows, please check if your GPU driver version is >= [31.0.101.5522](https://www.intel.cn/content/www/cn/zh/download/785597/823163/intel-arc-iris-xe-graphics-windows.html). If not, please follow the instructions in [this section](./install_windows_gpu.md#optional-update-gpu-driver) to update your GPU driver.
#### 12. Why my program can't find sycl device #### 12. Why my program can't find sycl device
If you meet `GGML_ASSERT: C:/Users/Administrator/actions-runner/cpp-release/_work/llm.cpp/llm.cpp/llama-cpp-bigdl/ggml-sycl.cpp:18283: main_gpu_id<g_all_sycl_device_count` error or similar error, and you find nothing is output when using `ls-sycl-device`, this is because llama.cpp cannot find the sycl device. On some laptops, the installation of the ARC driver may lead to a forced installation of `OpenCL, OpenGL, and Vulkan Compatibility Pack` by Microsoft, which inadvertently blocks the system from locating sycl devices. This issue can be resolved by manually uninstalling it in Microsoft store. If you meet `GGML_ASSERT: C:/Users/Administrator/actions-runner/cpp-release/_work/llm.cpp/llm.cpp/llama-cpp-bigdl/ggml-sycl.cpp:18283: main_gpu_id<g_all_sycl_device_count` error or similar error, and you find nothing is output when using `ls-sycl-device`, this is because llama.cpp cannot find the sycl device. On some laptops, the installation of the ARC driver may lead to a forced installation of `OpenCL, OpenGL, and Vulkan Compatibility Pack` by Microsoft, which inadvertently blocks the system from locating sycl devices. This issue can be resolved by manually uninstalling it in Microsoft store.

4
docs/mddocs/Quickstart/llama_cpp_quickstart.zh-CN.md
View file

@ -353,8 +353,8 @@ Log end
1. Windows：是否已经安装了 conda 并激活了正确的 conda 环境，环境中是否已经使用 pip 安装了 oneAPI 依赖项 1. Windows：是否已经安装了 conda 并激活了正确的 conda 环境，环境中是否已经使用 pip 安装了 oneAPI 依赖项
2. Linux：是否已经在运行 llama.cpp 命令前执行了 `source /opt/intel/oneapi/setvars.sh`。执行此 source 命令只在当前会话有效。 2. Linux：是否已经在运行 llama.cpp 命令前执行了 `source /opt/intel/oneapi/setvars.sh`。执行此 source 命令只在当前会话有效。
#### 11. 遇到输出乱码请先检查驱动 #### 11. 在 Windows 上遇到输出乱码请先检查驱动
如果你遇到输出乱码，请检查 GPU 驱动版本是否 >= [31.0.101.5522](https://www.intel.cn/content/www/cn/zh/download/785597/823163/intel-arc-iris-xe-graphics-windows.html)。如果不是，请参照[这里](./install_linux_gpu.zh-CN.md#安装-GPU-驱动程序) 的说明更新你的 GPU 驱动。 如果你在 Windows 上遇到输出乱码，请检查 GPU 驱动版本是否 >= [31.0.101.5522](https://www.intel.cn/content/www/cn/zh/download/785597/823163/intel-arc-iris-xe-graphics-windows.html)。如果不是，请参照[这里](./install_windows_gpu.zh-CN.md#可选-更新-gpu-驱动程序) 的说明更新你的 GPU 驱动。
#### 12. 为什么我的程序找不到 sycl 设备 #### 12. 为什么我的程序找不到 sycl 设备
如果你遇到 `GGML_ASSERT: C:/Users/Administrator/actions-runner/cpp-release/_work/llm.cpp/llm.cpp/llama-cpp-bigdl/ggml-sycl.cpp:18283: main_gpu_id<g_all_sycl_device_count` 错误或者类似错误，并且发现使用 `ls-sycl-device` 时没有任何输出，这是因为 llama.cpp 无法找到 sycl 设备。在某些笔记本电脑上，安装 ARC 驱动程序可能会导致被 Microsoft 强制安装 `OpenCL, OpenGL, and Vulkan Compatibility Pack`，这会无意中阻止系统定位 sycl 设备。这个问题可以通过在微软应用商店中手动卸载这个软件包来解决。 如果你遇到 `GGML_ASSERT: C:/Users/Administrator/actions-runner/cpp-release/_work/llm.cpp/llm.cpp/llama-cpp-bigdl/ggml-sycl.cpp:18283: main_gpu_id<g_all_sycl_device_count` 错误或者类似错误，并且发现使用 `ls-sycl-device` 时没有任何输出，这是因为 llama.cpp 无法找到 sycl 设备。在某些笔记本电脑上，安装 ARC 驱动程序可能会导致被 Microsoft 强制安装 `OpenCL, OpenGL, and Vulkan Compatibility Pack`，这会无意中阻止系统定位 sycl 设备。这个问题可以通过在微软应用商店中手动卸载这个软件包来解决。