[NPU] Add Gemma4 Sliding Window Attention support on Ascend backend (#26147)

test/manual/ascend/llm_models/test_npu_gemma_4_26b_a4b_it_llm.py

@@ -0,0 +1,30 @@
+import unittest
+
+from sglang.test.ascend.gsm8k_ascend_mixin import GSM8KAscendMixin
+from sglang.test.ascend.test_ascend_utils import GEMMA_4_26B_A4B_IT_WEIGHTS_PATH
+from sglang.test.test_utils import CustomTestCase
+
+
+class TestGemma426BA4BIt(GSM8KAscendMixin, CustomTestCase):
+    """Testcase: Verify that the inference accuracy of the google/gemma-4-26B-A4B-it model on the GSM8K dataset is no less than 0.35.
+
+    [Test Category] Model
+    [Test Target] google/gemma-4-26B-A4B-it
+    """
+
+    model = GEMMA_4_26B_A4B_IT_WEIGHTS_PATH
+    accuracy = 0.35
+    other_args = [
+        "--trust-remote-code",
+        "--mem-fraction-static",
+        "0.7",
+        "--attention-backend",
+        "ascend",
+        "--disable-cuda-graph",
+        "--tp-size",
+        "2",
+    ]
+
+
+if __name__ == "__main__":
+    unittest.main()

test/manual/ascend/llm_models/test_npu_gemma_4_31b_llm.py

@@ -0,0 +1,30 @@
+import unittest
+
+from sglang.test.ascend.gsm8k_ascend_mixin import GSM8KAscendMixin
+from sglang.test.ascend.test_ascend_utils import GEMMA_4_31B_WEIGHTS_PATH
+from sglang.test.test_utils import CustomTestCase
+
+
+class TestGemma431B(GSM8KAscendMixin, CustomTestCase):
+    """Testcase: Verify that the inference accuracy of the google/gemma-4-31B-it model on the GSM8K dataset is no less than 0.70.
+
+    [Test Category] Model
+    [Test Target] google/gemma-4-31B-it
+    """
+
+    model = GEMMA_4_31B_WEIGHTS_PATH
+    accuracy = 0.70
+    other_args = [
+        "--trust-remote-code",
+        "--mem-fraction-static",
+        "0.7",
+        "--attention-backend",
+        "ascend",
+        "--disable-cuda-graph",
+        "--tp-size",
+        "2",
+    ]
+
+
+if __name__ == "__main__":
+    unittest.main()

test/manual/ascend/llm_models/test_npu_gemma_4_e2b_llm.py

@@ -0,0 +1,30 @@
+import unittest
+
+from sglang.test.ascend.gsm8k_ascend_mixin import GSM8KAscendMixin
+from sglang.test.ascend.test_ascend_utils import GEMMA_4_E2B_WEIGHTS_PATH
+from sglang.test.test_utils import CustomTestCase
+
+
+class TestGemma4E2B(GSM8KAscendMixin, CustomTestCase):
+    """Testcase: Verify that the inference accuracy of the google/gemma-4-E2B-it model on the GSM8K dataset is no less than 0.05.
+
+    [Test Category] Model
+    [Test Target] google/gemma-4-E2B-it
+    """
+
+    model = GEMMA_4_E2B_WEIGHTS_PATH
+    accuracy = 0.05
+    other_args = [
+        "--trust-remote-code",
+        "--mem-fraction-static",
+        "0.7",
+        "--attention-backend",
+        "ascend",
+        "--disable-cuda-graph",
+        "--tp-size",
+        "1",
+    ]
+
+
+if __name__ == "__main__":
+    unittest.main()

test/manual/ascend/llm_models/test_npu_gemma_4_e4b_llm.py

@@ -0,0 +1,30 @@
+import unittest
+
+from sglang.test.ascend.gsm8k_ascend_mixin import GSM8KAscendMixin
+from sglang.test.ascend.test_ascend_utils import GEMMA_4_E4B_WEIGHTS_PATH
+from sglang.test.test_utils import CustomTestCase
+
+
+class TestGemma4E4B(GSM8KAscendMixin, CustomTestCase):
+    """Testcase: Verify that the inference accuracy of the google/gemma-4-E4B-it model on the GSM8K dataset is no less than 0.60.
+
+    [Test Category] Model
+    [Test Target] google/gemma-4-E4B-it
+    """
+
+    model = GEMMA_4_E4B_WEIGHTS_PATH
+    accuracy = 0.60
+    other_args = [
+        "--trust-remote-code",
+        "--mem-fraction-static",
+        "0.7",
+        "--attention-backend",
+        "ascend",
+        "--disable-cuda-graph",
+        "--tp-size",
+        "1",
+    ]
+
+
+if __name__ == "__main__":
+    unittest.main()

test/manual/ascend/vlm_models/test_npu_gemma_4_26b_a4b_it.py

@@ -0,0 +1,22 @@
+import unittest
+
+from sglang.test.ascend.test_ascend_utils import GEMMA_4_26B_A4B_IT_WEIGHTS_PATH
+from sglang.test.ascend.vlm_utils import TestVLMModels
+
+
+class TestGemma426BA4BIt(TestVLMModels):
+    """Testcase: Verify that the inference accuracy of the google/gemma-4-26B-A4B-it model on the MMMU dataset is no less than 0.40.
+
+    [Test Category] Model
+    [Test Target] google/gemma-4-26B-A4B-it
+    """
+
+    model = GEMMA_4_26B_A4B_IT_WEIGHTS_PATH
+    mmmu_accuracy = 0.40
+
+    def test_vlm_mmmu_benchmark(self):
+        self._run_vlm_mmmu_test()
+
+
+if __name__ == "__main__":
+    unittest.main()

test/manual/ascend/vlm_models/test_npu_gemma_4_31b.py

@@ -0,0 +1,22 @@
+import unittest
+
+from sglang.test.ascend.test_ascend_utils import GEMMA_4_31B_WEIGHTS_PATH
+from sglang.test.ascend.vlm_utils import TestVLMModels
+
+
+class TestGemma431B(TestVLMModels):
+    """Testcase: Verify that the inference accuracy of the google/gemma-4-31B-it model on the MMMU dataset is no less than 0.50.
+
+    [Test Category] Model
+    [Test Target] google/gemma-4-31B-it
+    """
+
+    model = GEMMA_4_31B_WEIGHTS_PATH
+    mmmu_accuracy = 0.50
+
+    def test_vlm_mmmu_benchmark(self):
+        self._run_vlm_mmmu_test()
+
+
+if __name__ == "__main__":
+    unittest.main()

test/manual/ascend/vlm_models/test_npu_gemma_4_e2b.py

@@ -0,0 +1,22 @@
+import unittest
+
+from sglang.test.ascend.test_ascend_utils import GEMMA_4_E2B_WEIGHTS_PATH
+from sglang.test.ascend.vlm_utils import TestVLMModels
+
+
+class TestGemma4E2B(TestVLMModels):
+    """Testcase: Verify that the inference accuracy of the google/gemma-4-E2B-it model on the MMMU dataset is no less than 0.15.
+
+    [Test Category] Model
+    [Test Target] google/gemma-4-E2B-it
+    """
+
+    model = GEMMA_4_E2B_WEIGHTS_PATH
+    mmmu_accuracy = 0.15
+
+    def test_vlm_mmmu_benchmark(self):
+        self._run_vlm_mmmu_test()
+
+
+if __name__ == "__main__":
+    unittest.main()

test/manual/ascend/vlm_models/test_npu_gemma_4_e4b.py

@@ -0,0 +1,22 @@
+import unittest
+
+from sglang.test.ascend.test_ascend_utils import GEMMA_4_E4B_WEIGHTS_PATH
+from sglang.test.ascend.vlm_utils import TestVLMModels
+
+
+class TestGemma4E4B(TestVLMModels):
+    """Testcase: Verify that the inference accuracy of the google/gemma-4-E4B-it model on the MMMU dataset is no less than 0.30.
+
+    [Test Category] Model
+    [Test Target] google/gemma-4-E4B-it
+    """
+
+    model = GEMMA_4_E4B_WEIGHTS_PATH
+    mmmu_accuracy = 0.30
+
+    def test_vlm_mmmu_benchmark(self):
+        self._run_vlm_mmmu_test()
+
+
+if __name__ == "__main__":
+    unittest.main()