Open Yanli2190 opened 4 weeks ago
Hi @Yanli2190 , we will try to reproduce your problem.
Hi @Yanli2190 , we used your code and tried to reproduce on our Flex machine. The result is similar to yours which has a maximum utilization of 84%.
GPU Power is more accurate when using xpu-smi, Flex170 max power: 150w, GPU power got via xpu-smi is 60w when running whisper when running llama, GPU power got via xpu-smi is ~128w, almost max GPU SOC power, which means that GPU is fully utilized.
Summary:
Steps:
Install ipex-llm following below steps(20240629 is used): conda create -n ipex_llm python=3.9 source activate ipex_llm conda install -c conda-forge -y libstdcxx-ng=12 conda install -c conda-forge -y gperftools=2.10 jemalloc==5.2.1 pip install --pre --upgrade ipex-llm[xpu] --extra-index-url https://pytorch-extension.intel.com/release-whl/stable/xpu/us/ pip install datasets soundfile librosa
Run whisper via ipex-llm following run.sh(rename run.txt to run.sh, rename run_whipser_base_perf_dataset.txt to run_whipser_base_perf_dataset.py) run.txt run_whipser_base_perf_dataset.txt
Monitor GPU Usage via xpu-smi