diff --git a/vllm/model_executor/layers/quantization/bitsandbytes.py b/vllm/model_executor/layers/quantization/bitsandbytes.py
index 983c076bd..0d6d0bac9 100644
--- a/vllm/model_executor/layers/quantization/bitsandbytes.py
+++ b/vllm/model_executor/layers/quantization/bitsandbytes.py
@@ -336,16 +336,6 @@ class BitsAndBytesLinearMethod(LinearMethodBase):
 
             current_index += output_size
 
-            # only update the matmul_states if it is not profile_run
-            if (
-                generation > 0
-                and not self.quant_config.llm_int8_has_fp16_weight
-                and matmul_states[i].CB is not None
-                and matmul_states[i].CxB is not None
-            ):
-                del matmul_states[i].CB
-                qweight[offsets[i] : offsets[i + 1]] = matmul_states[i].CxB
-
         out = out.to(original_type)
 
         if reshape_after_matmul: