From 15d906a97bdb5499fd11b092cbbff360310b6009 Mon Sep 17 00:00:00 2001 From: Zhao Changmin Date: Wed, 22 May 2024 17:18:07 +0800 Subject: [PATCH] Update linux igpu run script (#11098) * update run script --- .../source/doc/LLM/Quickstart/benchmark_quickstart.md | 8 ++++++++ python/llm/dev/benchmark/all-in-one/run-igpu.sh | 6 ++++++ 2 files changed, 14 insertions(+) create mode 100644 python/llm/dev/benchmark/all-in-one/run-igpu.sh diff --git a/docs/readthedocs/source/doc/LLM/Quickstart/benchmark_quickstart.md b/docs/readthedocs/source/doc/LLM/Quickstart/benchmark_quickstart.md index 6bd48e87..2993ba0a 100644 --- a/docs/readthedocs/source/doc/LLM/Quickstart/benchmark_quickstart.md +++ b/docs/readthedocs/source/doc/LLM/Quickstart/benchmark_quickstart.md @@ -113,6 +113,14 @@ Please refer to [here](https://ipex-llm.readthedocs.io/en/latest/doc/LLM/Overvie ./run-arc.sh + .. tab:: Intel iGPU + + For Intel iGPU, we recommend: + + .. code-block:: bash + + ./run-igpu.sh + .. tab:: Intel Data Center GPU Max Please note that you need to run ``conda install -c conda-forge -y gperftools=2.10`` before running the benchmark script on Intel Data Center GPU Max Series. diff --git a/python/llm/dev/benchmark/all-in-one/run-igpu.sh b/python/llm/dev/benchmark/all-in-one/run-igpu.sh new file mode 100644 index 00000000..7f884196 --- /dev/null +++ b/python/llm/dev/benchmark/all-in-one/run-igpu.sh @@ -0,0 +1,6 @@ +source /opt/intel/oneapi/setvars.sh + +export SYCL_CACHE_PERSISTENT=1 +export BIGDL_LLM_XMX_DISABLED=1 + +python run.py # make sure config YAML file