Support generation search for transformers examples (#2029)

Signed-off-by: Kaihui-intel <kaihui.tang@intel.com>

.pre-commit-config.yaml

@@ -76,7 +76,7 @@ repos:
           )$
 
   - repo: https://github.com/PyCQA/docformatter
-    rev: v1.7.5
+    rev: 06907d0
     hooks:
       - id: docformatter
         args: [

examples/3.x_api/pytorch/nlp/huggingface_models/language-modeling/quantization/transformers/weight_only/text-generation/run_generation_gpu_woq.py

@@ -8,6 +8,7 @@
 import intel_extension_for_pytorch as ipex
 from neural_compressor.transformers import AutoModelForCausalLM, AutoRoundConfig, RtnConfig, GPTQConfig
 from neural_compressor.transformers.quantization.utils import convert_dtype_str2torch
+from neural_compressor.transformers.generation import _greedy_search, _beam_search
 from transformers.utils import check_min_version
 import contextlib
 

neural_compressor/transformers/generation/__init__.py

@@ -0,0 +1,19 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+#
+# Copyright (c) 2024 Intel Corporation
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#   http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+from .beam_search import _beam_search
+from .greedy_search import _greedy_search