[GHA] replaced benchmark_genai-ubuntu (#1817)

replaced benchmark_genai-ubuntu pipeline

Author: mryzhov

.github/workflows/causal_lm_cpp.yml

@@ -269,42 +269,6 @@ jobs:
           diff pred2.txt ref.txt
           echo "Chat sample python" passed
 
-  benchmark_genai-ubuntu:
-    runs-on: ubuntu-24.04
-    defaults:
-      run:
-        shell: bash
-    steps:
-      - uses: actions/checkout@v4
-        with:
-          submodules: recursive
-      - uses: actions/setup-python@v4
-        with:
-          python-version: 3.11
-      - name: Install OpenVINO
-        run: |
-          mkdir ./ov/
-          curl ${{ env.l_ov_link }} | tar --directory ./ov/ --strip-components 1 -xz
-          sudo ./ov/install_dependencies/install_openvino_dependencies.sh
-      - name: Build app
-        run: |
-          source ./ov/setupvars.sh
-          cmake -DCMAKE_BUILD_TYPE=Release -S ./ -B ./build/
-          cmake --build ./build/ --config Release -j
-      - name: Download and convert and model
-        run: |
-          source ./ov/setupvars.sh
-          python -m pip install ./thirdparty/openvino_tokenizers/[transformers] --extra-index-url https://storage.openvinotoolkit.org/simple/wheels/nightly
-          python -m pip install -r ./samples/requirements.txt
-          optimum-cli export openvino --trust-remote-code --weight-format fp16 --model TinyLlama/TinyLlama-1.1B-Chat-v1.0 TinyLlama-1.1B-Chat-v1.0
-      - name: Run
-        env:
-          PYTHONPATH: "./build"
-        run: |
-          source ./ov/setupvars.sh
-          timeout 60s ./build/samples/cpp/text_generation/benchmark_genai -m ./TinyLlama-1.1B-Chat-v1.0/ -p "Why is the sun yellow?" --nw 2 -n 3 --mt 50 -d CPU
-          timeout 60s  python ./samples/python/text_generation/benchmark_genai.py -m ./TinyLlama-1.1B-Chat-v1.0/ -p "Why is the sun yellow?" -nw 2 -n 3 -mt 50 -d CPU
-
   visual_language_chat_sample-ubuntu-minicpm_v2_6:
     runs-on: ubuntu-22.04-16-cores
     steps:

tests/python_tests/samples/test_benchmark_genai.py

@@ -0,0 +1,40 @@
+# Copyright (C) 2025 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+import os
+import pytest
+import sys
+
+from conftest import SAMPLES_PY_DIR, SAMPLES_CPP_DIR
+from test_utils import run_sample
+
+class TestBenchmarkGenAI:
+    @pytest.mark.llm
+    @pytest.mark.samples
+    @pytest.mark.parametrize(
+        "convert_model, prompt, sample_args",
+        [
+            pytest.param("TinyLlama-1.1B-Chat-v1.0", "Why is the sun yellow?", ["-nw", "2", "-n", "3", "-mt", "50", "-d", "CPU"]),
+        ],
+        indirect=["convert_model"],
+    )
+    def test_py_sample_benchmark_genai(self, convert_model, prompt, sample_args):
+        # Test Python sample
+        py_script = os.path.join(SAMPLES_PY_DIR, "text_generation/benchmark_genai.py")
+        py_command = [sys.executable, py_script, '-m', convert_model, '-p', f'"{prompt}"'] + sample_args
+        run_sample(py_command)
+
+    @pytest.mark.llm
+    @pytest.mark.samples
+    @pytest.mark.parametrize(
+        "convert_model, prompt, sample_args",
+        [
+            pytest.param("TinyLlama-1.1B-Chat-v1.0", "Why is the sun yellow?", ["--nw", "2", "-n", "3", "--mt", "50", "-d", "CPU"]),
+        ],
+        indirect=["convert_model"],
+    )
+    def test_cpp_sample_benchmark_genai(self, convert_model, prompt, sample_args):
+        # Test CPP sample
+        cpp_sample = os.path.join(SAMPLES_CPP_DIR, 'benchmark_genai')
+        cpp_command =[cpp_sample, '-m', convert_model, '-p', f'"{prompt}"'] + sample_args
+        run_sample(cpp_command)