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

Update runtime configuration on MTL (#12720)

Browse source
This commit is contained in:
Yuwen Hu 2025-01-20 11:06:37 +08:00 committed by GitHub
parent bda87c21eb
commit 9aa4be8ced
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 0 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

1
python/llm/src/ipex_llm/transformers/npu_models/convert_mp.py
View file

@ -34,7 +34,6 @@ def optimize_llm_pre(model: torch.nn.Module, qtype, mixed_precision,
quantization_group_size=0, load=False, max_prompt_len=512): quantization_group_size=0, load=False, max_prompt_len=512):
if os.environ.get("IPEX_LLM_NPU_MTL", "0") == "1": if os.environ.get("IPEX_LLM_NPU_MTL", "0") == "1":
# For MTL support # For MTL support
os.environ["IPEX_LLM_NPU_USE_LEVEL0"] = "0"
os.environ["IPEX_LLM_NPU_DISABLE_COMPILE_OPT"] = "1" os.environ["IPEX_LLM_NPU_DISABLE_COMPILE_OPT"] = "1"
if os.environ.get("IPEX_LLM_NPU_ARL", "0") == "1": if os.environ.get("IPEX_LLM_NPU_ARL", "0") == "1":