[NPU] Hot fix of load_low_bit (#12344)

intel-analytics · Nov 6, 2024 · 69e3a56 · 69e3a56
1 parent 899a303
commit 69e3a56
Showing 1 changed file with 1 addition and 1 deletion.
diff --git a/python/llm/src/ipex_llm/transformers/npu_model.py b/python/llm/src/ipex_llm/transformers/npu_model.py
@@ -549,7 +549,7 @@ def load_low_bit(cls, pretrained_model_name_or_path: str, *model_args, **kwargs)
             from ipex_llm.transformers.npu_models.convert_mp import optimize_llm
             optimize_llm(
                 llm,
-                max_output_len=max_context_len,
+                max_context_len=max_context_len,
                 max_prompt_len=max_prompt_len,
                 inter_pp=inter_pp,
                 intra_pp=intra_pp,