[NPU] Hot fix of load_low_bit (#12344)

2024-11-06 10:07:00 +08:00 · 2024-11-06 10:07:00 +08:00 · 69e3a56943
commit 69e3a56943
parent 899a30331a
1 changed files with 1 additions and 1 deletions
--- a/python/llm/src/ipex_llm/transformers/npu_model.py
+++ b/python/llm/src/ipex_llm/transformers/npu_model.py
@ -549,7 +549,7 @@ class _BaseAutoModelClass:
            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,