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

[Doc] Update ipex-llm ollama troubleshooting for v0.4.6 (#12642)

Browse source 
* update ollama v0.4.6 troubleshooting

* update chinese ollama-doc
This commit is contained in:
SONG Ge 2025-01-02 17:28:54 +08:00 committed by GitHub
parent 8e5328e9b4
commit 550fa01649
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 14 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

7
docs/mddocs/Quickstart/ollama_quickstart.md
View file

@ -78,6 +78,7 @@ You may launch the Ollama service as below:
export OLLAMA_NUM_GPU=999
export no_proxy=localhost,127.0.0.1
export ZES_ENABLE_SYSMAN=1
source /opt/intel/oneapi/setvars.sh
export SYCL_CACHE_PERSISTENT=1
# [optional] under most circumstances, the following environment variable may improve performance, but sometimes this may also cause performance degradation
@ -227,3 +228,9 @@ If you meet this error, please check your Linux kernel version first. You may en
#### 8. Save GPU memory by specify `OLLAMA_NUM_PARALLEL=1`
If you have a limited GPU memory, use `set OLLAMA_NUM_PARALLEL=1` on Windows or `export OLLAMA_NUM_PARALLEL=1` on Linux before `ollama serve` to reduce GPU usage. The default `OLLAMA_NUM_PARALLEL` in ollama upstream is set to 4.
#### 9. `cannot open shared object file` error when executing `ollama serve`
When executing `ollama serve` and `ollama run <model_name>`, if you meet `./ollama: error while loading shared libraries: libsvml.so: cannot open shared object file: No such file or directory` on Linux, or if executing `ollama serve` and `ollama run <model_name>` shows no response on Windows, this is most likely caused by the lack of sycl dependency. Please check:
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 have executed `source /opt/intel/oneapi/setvars.sh` before running both `./ollama serve` and `./ollama run <model_name>` on Linux

7
docs/mddocs/Quickstart/ollama_quickstart.zh-CN.md
View file

@ -78,6 +78,7 @@ IPEX-LLM 现在已支持在 Linux 和 Windows 系统上运行 `Ollama`。
export OLLAMA_NUM_GPU=999
export no_proxy=localhost,127.0.0.1
export ZES_ENABLE_SYSMAN=1
source /opt/intel/oneapi/setvars.sh
export SYCL_CACHE_PERSISTENT=1
# [optional] under most circumstances, the following environment variable may improve performance, but sometimes this may also cause performance degradation
@ -222,3 +223,9 @@ Ollama 默认每 5 分钟从 GPU 内存卸载一次模型。针对 ollama 的最
#### 8. 通过设置`OLLAMA_NUM_PARALLEL=1`节省GPU内存
如果你的GPU内存较小，可以通过在运行`ollama serve`前运行`set OLLAMA_NUM_PARALLEL=1`（Windows）或`export OLLAMA_NUM_PARALLEL=1`（Linux）来减少内存使用。Ollama默认使用的`OLLAMA_NUM_PARALLEL`为4。
#### 9. 执行 `ollama serve`时报 `cannot open shared object file` 错误
执行 `ollama serve` 或 `ollama run <model_name>` 时，如果你在 Linux 上遇到 `./ollama: error while loading shared libraries: libsvml.so: cannot open shared object file: No such file or directory`，或者在 Windows 上执行 `ollama serve` 和 `ollama run <model_name>` 时没有反应，这很可能是由于缺少 sycl 依赖导致的。请检查：
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 `./ollama serve` 和 `./ollama run <model_name>` 命令前都执行了 `source /opt/intel/oneapi/setvars.sh`。执行此 source 命令只在当前会话有效。