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

Disable llama2 optimize model true or false test for now in Arc UTs (#10008)

Browse source
This commit is contained in:
Yuwen Hu 2024-01-26 14:42:11 +08:00 committed by GitHub
parent a00efa0564
commit f0da0c131b
1 changed files with 2 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

3
python/llm/test/inference_gpu/test_transformers_api_disable_xmx.py
View file

@ -27,7 +27,8 @@ prompt = "Once upon a time, there existed a little girl who liked to have advent
@pytest.mark.parametrize('Model, Tokenizer, model_path',[
(AutoModelForCausalLM, AutoTokenizer, os.environ.get('MPT_7B_ORIGIN_PATH')),
(AutoModelForCausalLM, AutoTokenizer, os.environ.get('LLAMA2_7B_ORIGIN_PATH'))
# (AutoModelForCausalLM, AutoTokenizer, os.environ.get('LLAMA2_7B_ORIGIN_PATH')),
(AutoModelForCausalLM, AutoTokenizer, os.environ.get('FALCON_7B_ORIGIN_PATH')),
])
def test_optimize_model(Model, Tokenizer, model_path):
with torch.inference_mode():