Ruonan Wang

> 2.1.0b20240513 doesn't work for me. Same error again: `Error: [0] server cpu not listed in available servers map` Hi @tardigrade34 , I want to make sure if you have...

> > Error: [0] server cpu not listed in available servers map > I compile the newest ollama，generate the binary：ollama.exe, app.exe。I start ollama.exe and app.exe，when I run “ollama.exe run qwen:7b”，encounter...

I will close this issue first, if you meet any other issues, you can reopen it or raise a new issue about it.

Hi @digitalscream , based on our local test, Llama3 could get ~50 tokens/s on a **single A770**. > I was originally getting ~50t/s on inference, ran a rebuild (still with...

> Sorry, should've mentioned - that's using a single A770, the only change in the Docker image was that it pulled the `intelanalytics/ipex-llm-xpu:latest` base image again. I do have some...

Hi @tristan-k If I understand correctly, are you running llama.cpp on your integrated graphics (Intel (R) Iris (R) Xe Graphics) on an Ubuntu system? We have located the possible reasons...

Now ipex-llm has some issues for such unmerged lora module during inference. Maybe you can try to merge the lora module first and then use low-bit quantization. For example, update...

Hi @ElliottDyson This error (`mkl_sycl_blas.4.dll was not found`) is caused by missing of oneapi. Have you rightly install oneapi 2024.0 and source it by `call "C:\Program Files (x86)\Intel\oneAPI\setvars.bat"` (if you...

Hi @ElliottDyson , Suppose you have two conda enviroments, and just named them `llm-cpp` for cpp-based and `llm` for transformers-based code, Is your question why you can run the program...

Hi @markussiebert , sadly we can not reproduce this error on our A770 machine with https://github.com/ipex-llm/ipex-llm/releases/download/v2.3.0-nightly/llama-cpp-ipex-llm-2.3.0b20250612-ubuntu-core.tgz. And below is my log & cmd. ```bash export ONEAPI_DEVICE_SELECTOR=level_zero:0 export SYCL_PI_LEVEL_ZERO_USE_IMMEDIATE_COMMANDLISTS=1 ./llama-server -m...