SONG Ge comments

Results 166 comments of


                                            SONG Ge

llama runner process has terminated exit status 1

hi @dayskk , could you please run the ENV-Check script in https://github.com/intel-analytics/ipex-llm/tree/main/python/llm/scripts and reply us with the results?

Ollama not utilizing ARC A770 GPU on a Windows 11 Pro install

Hi @SG-Python1 , 1. Could you provide the output of `ollama serve` when doing model inference. 2. You may run the ENV-Check script in https://github.com/intel-analytics/ipex-llm/tree/main/python/llm/scripts and reply us with the...

Error loading model

Hi @yu1chaofan , you may set `export BIGDL_IMPORT_IPEX=0` before launching the webui.

Error loading model

> Am I missing some package? Or am I doing something wrong? `set BIGDL_IMPORT_IPEX=0` only works in cmd, you may run `$env:BIGDL_IMPORT_IPEX="0"` in powershell.

Error loading model

Hi @yu1chaofan , we have fixed this issue and released a new version of webui, you may update to our latest version and try again.

Text Generation WebUI issue

hi @wluo1007 , we have reproduced your issue. We will inform you once we make progress.

Text Generation WebUI issue

Hi @wluo1007 , you may set `export BIGDL_IMPORT_IPEX=0` before launching the webui.

Text Generation WebUI issue

@niceTeen84 , `python server.py --load-in-4bit --listen --listen-host 0.0.0.0 --listen-port 8080`

(PI_ERROR_DEVICE_NOT_FOUND) llama_load_model_from_file: exception loading model

Hi @sundeepChandhoke , yes ollama is expecting a gpu and it does not support running on a device without any gpu currently.

[documentation] "Quick Start" needs an actual Quick start

Thank you for using IPEX-LLM. We will discuss the support for Ubuntu 24.04 and update the corresponding document.