restruct compressed_tensors_w8a8_fp8 (#5475)

test/srt/models/test_compressed_tensors_models.py

@@ -0,0 +1,46 @@
+import unittest
+from types import SimpleNamespace
+
+from sglang.srt.utils import kill_process_tree
+from sglang.test.few_shot_gsm8k import run_eval
+from sglang.test.test_utils import (
+    DEFAULT_TIMEOUT_FOR_SERVER_LAUNCH,
+    DEFAULT_URL_FOR_TEST,
+    CustomTestCase,
+    popen_launch_server,
+)
+
+
+class TestCompressedTensorsLlama3FP8(CustomTestCase):
+    @classmethod
+    def setUpClass(cls):
+        cls.model = "RedHatAI/Meta-Llama-3.1-8B-FP8"
+        cls.base_url = DEFAULT_URL_FOR_TEST
+        cls.process = popen_launch_server(
+            cls.model,
+            cls.base_url,
+            timeout=DEFAULT_TIMEOUT_FOR_SERVER_LAUNCH,
+            other_args=[],
+        )
+
+    @classmethod
+    def tearDownClass(cls):
+        kill_process_tree(cls.process.pid)
+
+    def test_gsm8k(self):
+        args = SimpleNamespace(
+            num_shots=5,
+            data_path=None,
+            num_questions=200,
+            max_new_tokens=512,
+            parallel=128,
+            host="http://127.0.0.1",
+            port=int(self.base_url.split(":")[-1]),
+        )
+        metrics = run_eval(args)
+        print(f"{metrics=}")
+        self.assertGreater(metrics["accuracy"], 0.45)
+
+
+if __name__ == "__main__":
+    unittest.main()

test/srt/run_suite.py

@@ -20,6 +20,7 @@ suites = {
         TestFile("models/test_generation_models.py", 103),
         TestFile("models/test_grok_models.py", 60),
         TestFile("models/test_qwen_models.py", 82),
+        TestFile("models/test_compressed_tensors_models.py", 100),
         TestFile("models/test_reward_models.py", 83),
         TestFile("models/test_gme_qwen_models.py", 45),
         TestFile("models/test_clip_models.py", 100),