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

LLM: Small fix for benchmark userguide (#10373)

Browse source 
* small fix for benchmark userguide

* resolve some comments
This commit is contained in:
WeiguangHan 2024-03-12 12:26:26 +08:00 committed by GitHub
parent 490cbcc897
commit cac96b00be
1 changed files with 2 additions and 4 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

6
docs/readthedocs/source/doc/LLM/Quickstart/benchmark_quickstart.md
View file

@ -29,7 +29,6 @@ repo_id:
local_model_hub: '/mnt/disk1/models' local_model_hub: '/mnt/disk1/models'
warm_up: 1 warm_up: 1
num_trials: 3 num_trials: 3
num_beams: 1 # default to greedy search
low_bit: 'sym_int4' # default to use 'sym_int4' (i.e. symmetric int4) low_bit: 'sym_int4' # default to use 'sym_int4' (i.e. symmetric int4)
batch_size: 1 # default to 1 batch_size: 1 # default to 1
in_out_pairs: in_out_pairs:
@ -79,6 +78,7 @@ Please refer to [here](https://bigdl.readthedocs.io/en/latest/doc/LLM/Overview/i
.. tab:: Other Intel dGPU Series .. tab:: Other Intel dGPU Series
.. code-block:: bash .. code-block:: bash
# e.g. Arc™ A770 # e.g. Arc™ A770
python run.py python run.py
@ -98,14 +98,12 @@ Please refer to [here](https://bigdl.readthedocs.io/en/latest/doc/LLM/Overview/i
.. tab:: Intel Data Center GPU Max .. tab:: Intel Data Center GPU Max
For Intel Data Center GPU Max Series, we recommend: 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.
.. code-block:: bash .. code-block:: bash
./run-max-gpu.sh ./run-max-gpu.sh
Please note that you need to run ``conda install -c conda-forge -y gperftools=2.10`` to install essential dependencies for Intel Data Center GPU Max.
``` ```
## Result ## Result