[Misc] Clean up the BitsAndBytes arguments (#15140)

Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
2025-03-21 10:17:12 +08:00
parent d3ccbd6350
commit 10f55fe6c5
3 changed files with 7 additions and 15 deletions
--- a/examples/offline_inference/lora_with_quantization_inference.py
+++ b/examples/offline_inference/lora_with_quantization_inference.py
@@ -83,7 +83,6 @@ def initialize_engine(model: str, quantization: str,
        engine_args = EngineArgs(model=model,
                                 quantization=quantization,
                                 qlora_adapter_name_or_path=lora_repo,
-                                 load_format="bitsandbytes",
                                 enable_lora=True,
                                 max_lora_rank=64)
    else: