[Kernel] Disable CUTLASS kernels for fp8 (#5505)

Author: tlrmchlsmth

vllm/model_executor/layers/quantization/fp8.py

@@ -257,7 +257,9 @@ def apply(self,
         #   If dynamic, layer.input_scale is None and x_scale computed from x.
         #   If static, layer.input_scale is scalar and x_scale is input_scale.
 
-        if bias is None and self.cutlass_fp8_supported:
+        # Temporarily disable CUTLASS kernels due to an illegal memory access
+        #if  bias is None and self.cutlass_fp8_supported:
+        if False:
             qinput, x_scale = ops.scaled_fp8_quant(x, layer.input_scale)
 
             # Fused GEMM_DQ