[Feature] Support Ernie FP8 on sm100 ( the fixed version) (#6304)

fastdeploy/model_executor/layers/utils.py

@@ -254,7 +254,10 @@ def per_block_cast_to_fp8(x: Tensor, block_size: list = [128, 128]) -> Tuple[Ten
     Only used in deep_gemm block wise quant weight.
     copy from FastDeploy/custom_ops/gpu_ops/fp8_deep_gemm/tests/test_core.py.
     """
-    from fastdeploy.model_executor.ops.gpu.deep_gemm import ceil_div
+    try:
+        from deep_gemm import ceil_div
+    except ModuleNotFoundError:
+        from fastdeploy.model_executor.ops.gpu.deep_gemm import ceil_div
 
     assert x.dim() == 2
     m, n = x.shape
@@ -551,6 +554,12 @@ def vocab_range_from_global_vocab_size(global_vocab_size: int, rank: int, world_
     return vocab_range_from_per_partition_vocab_size(per_partition_vocab_size, rank, offset=offset)
 
 
+def get_sm_version():
+    prop = paddle.device.cuda.get_device_properties()
+    cc = prop.major * 10 + prop.minor
+    return cc
+
+
 def modules_to_convert(prefix: str, fd_config: FDConfig):
     import fnmatch