Attempt to put ck blockscale back in for mi300

Author: Doug Lehr

vllm/model_executor/layers/quantization/utils/fp8_utils.py

@@ -54,11 +54,11 @@ def rocm_aiter_gemm_w8a8_blockscale_impl(
     block_size: list[int],
     output_dtype: torch.dtype = torch.float16,
 ) -> torch.Tensor:
-    # import aiter as rocm_aiter
-
-    # return rocm_aiter.gemm_a8w8_blockscale(A, B, As, Bs, dtype=output_dtype)
-    from aiter.ops.triton.gemm_a8w8_blockscale import gemm_a8w8_blockscale
-
+    # MI300's fp8nuz should be enough to detect if we call ck vs triton
+    if current_platform.is_fp8_fnuz():
+        from aiter import gemm_a8w8_blockscale
+    else:
+        from aiter.ops.triton.gemm_a8w8_blockscale import gemm_a8w8_blockscale
     return gemm_a8w8_blockscale(A, B, As, Bs, dtype=output_dtype)