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

add troubleshooting section (#12755)

Browse source
This commit is contained in:
Shaojun Liu 2025-01-26 11:03:58 +08:00 committed by GitHub
parent 5fb87d7486
commit ee809e71df
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 23 additions and 3 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

24
docs/mddocs/Quickstart/bmg_quickstart.md
View file

@ -13,15 +13,17 @@ This guide demonstrates how to install and use IPEX-LLM on the Intel Arc B-Serie
1.1 [Install Prerequisites](#11-install-prerequisites) 1.1 [Install Prerequisites](#11-install-prerequisites)
1.2 [Install IPEX-LLM](#for-pytorch-and-huggingface) (for PyTorch and HuggingFace) 1.2 [Install IPEX-LLM](#for-pytorch-and-huggingface) (for PyTorch and HuggingFace)
1.3 [Install IPEX-LLM](#for-llamacpp-and-ollama) (for llama.cpp and Ollama) 1.3 [Install IPEX-LLM](#for-llamacpp-and-ollama) (for llama.cpp and Ollama)
3. [Windows](#2-windows) 2. [Windows](#2-windows)
2.1 [Install Prerequisites](#21-install-prerequisites) 2.1 [Install Prerequisites](#21-install-prerequisites)
2.2 [Install IPEX-LLM](#for-pytorch-and-huggingface-1) (for PyTorch and HuggingFace) 2.2 [Install IPEX-LLM](#for-pytorch-and-huggingface-1) (for PyTorch and HuggingFace)
2.3 [Install IPEX-LLM](#for-llamacpp-and-ollama-1) (for llama.cpp and Ollama) 2.3 [Install IPEX-LLM](#for-llamacpp-and-ollama-1) (for llama.cpp and Ollama)
5. [Use Cases](#3-use-cases) 3. [Use Cases](#3-use-cases)
3.1 [PyTorch](#31-pytorch) 3.1 [PyTorch](#31-pytorch)
3.2 [Ollama](#32-ollama) 3.2 [Ollama](#32-ollama)
3.3 [llama.cpp](#33-llamacpp) 3.3 [llama.cpp](#33-llamacpp)
3.4 [vLLM](#34-vllm) 3.4 [vLLM](#34-vllm)
4. [Troubleshooting](#4-troubleshooting)
4.1 [RuntimeError: could not create an engine](#41-runtimeerror-could-not-create-an-engine)
--- ---
## 1. Linux ## 1. Linux
@ -180,3 +182,21 @@ For instructions on how to run **llama.cpp** with IPEX-LLM, refer to the [llama.
To set up and run **vLLM**, follow the [vLLM Quickstart guide](https://github.com/intel-analytics/ipex-llm/blob/main/docs/mddocs/Quickstart/vLLM_quickstart.md). To set up and run **vLLM**, follow the [vLLM Quickstart guide](https://github.com/intel-analytics/ipex-llm/blob/main/docs/mddocs/Quickstart/vLLM_quickstart.md).
## 4. Troubleshooting
### 4.1 RuntimeError: could not create an engine
![image](https://github.com/user-attachments/assets/757f0704-9240-46d0-bceb-661fecc96182)
If you encounter a `RuntimeError` like the output shown above while working on Linux after running `conda deactivate` and then reactivating your environment using `conda activate env`, the issue is likely caused by the `OCL_ICD_VENDORS` environment variable.
To fix this on Linux, run the following command:
```bash
unset OCL_ICD_VENDORS
```
This will remove the conflicting environment variable and allow your program to function correctly.
**Note:** This issue only occurs on Linux systems. It does not affect Windows environments.