Remove dead bitsandbytes CxB code from 8-bit inference path (vllm-project#34633)

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>

Author: TimDettmers

vllm/model_executor/layers/quantization/bitsandbytes.py

@@ -336,16 +336,6 @@ def _apply_8bit_weight(
 
             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: