From 9aa4be8ced56f70f49e8d82d4ccb7a7218ec0467 Mon Sep 17 00:00:00 2001 From: Yuwen Hu <54161268+Oscilloscope98@users.noreply.github.com> Date: Mon, 20 Jan 2025 11:06:37 +0800 Subject: [PATCH] Update runtime configuration on MTL (#12720) --- python/llm/src/ipex_llm/transformers/npu_models/convert_mp.py | 1 - 1 file changed, 1 deletion(-) diff --git a/python/llm/src/ipex_llm/transformers/npu_models/convert_mp.py b/python/llm/src/ipex_llm/transformers/npu_models/convert_mp.py index ede8d88e613..4102e23ecea 100644 --- a/python/llm/src/ipex_llm/transformers/npu_models/convert_mp.py +++ b/python/llm/src/ipex_llm/transformers/npu_models/convert_mp.py @@ -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): if os.environ.get("IPEX_LLM_NPU_MTL", "0") == "1": # For MTL support - os.environ["IPEX_LLM_NPU_USE_LEVEL0"] = "0" os.environ["IPEX_LLM_NPU_DISABLE_COMPILE_OPT"] = "1" if os.environ.get("IPEX_LLM_NPU_ARL", "0") == "1":