Remove the torchao integration (--torchao-config) (#34304)

Co-authored-by: Brayden Zhong <brayden@radixark.ai>

test/manual/quant/test_torchao.py

@@ -1,92 +0,0 @@
-import unittest
-
-import requests
-from transformers import AutoProcessor
-
-from sglang import Engine
-from sglang.srt.utils import kill_process_tree
-from sglang.test.kits.eval_accuracy_kit import MMLUMixin
-from sglang.test.test_utils import (
-    DEFAULT_IMAGE_URL,
-    DEFAULT_MODEL_NAME_FOR_TEST,
-    DEFAULT_SMALL_VLM_MODEL_NAME_FOR_TEST,
-    DEFAULT_TIMEOUT_FOR_SERVER_LAUNCH,
-    DEFAULT_URL_FOR_TEST,
-    CustomTestCase,
-    build_vlm_image_prompt,
-    is_in_amd_ci,
-    popen_launch_server,
-)
-
-
-class TestTorchAO(CustomTestCase, MMLUMixin):
-    mmlu_score_threshold = 0.60
-    mmlu_num_examples = 64
-    mmlu_num_threads = 32
-
-    @classmethod
-    def setUpClass(cls):
-        cls.model = DEFAULT_MODEL_NAME_FOR_TEST
-        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=["--torchao-config", "int4wo-128"],
-        )
-
-    @classmethod
-    def tearDownClass(cls):
-        kill_process_tree(cls.process.pid)
-
-    def run_decode(self, max_new_tokens):
-        response = requests.post(
-            self.base_url + "/generate",
-            json={
-                "text": "The capital of France is",
-                "sampling_params": {
-                    "temperature": 0,
-                    "max_new_tokens": max_new_tokens,
-                },
-                "ignore_eos": True,
-            },
-        )
-        return response.json()
-
-    def test_throughput(self):
-        import time
-
-        max_tokens = 256
-
-        tic = time.perf_counter()
-        res = self.run_decode(max_tokens)
-        tok = time.perf_counter()
-        print(res["text"])
-        throughput = max_tokens / (tok - tic)
-        print(f"Throughput: {throughput} tokens/s")
-        if is_in_amd_ci():
-            assert throughput >= 150
-        else:
-            assert throughput >= 210
-
-
-class TestTorchAOForVLM(CustomTestCase):
-    def test_vlm_generate(self):
-        model_path = DEFAULT_SMALL_VLM_MODEL_NAME_FOR_TEST
-        text = build_vlm_image_prompt(
-            AutoProcessor.from_pretrained(model_path), "What is in this picture?"
-        )
-
-        engine = Engine(
-            model_path=model_path,
-            max_total_tokens=512,
-            enable_multimodal=True,
-            torchao_config="fp8wo",
-        )
-        out = engine.generate([text], image_data=[DEFAULT_IMAGE_URL])
-        engine.shutdown()
-        self.assertGreater(len(out), 0)
-
-
-if __name__ == "__main__":
-    unittest.main()

test/manual/test_srt_engine_with_quant_args.py

@@ -32,29 +32,6 @@ class TestSRTEngineWithQuantArgs(CustomTestCase):
             engine.generate(prompt, sampling_params)
             engine.shutdown()
 
-    def test_2_torchao_args(self):
-
-        # we don't test int8dq because currently there is conflict between int8dq and capture cuda graph
-        torchao_args_list = [
-            # "int8dq",
-            "int8wo",
-            "fp8wo",
-            "fp8dq-per_tensor",
-            "fp8dq-per_row",
-        ] + [f"int4wo-{group_size}" for group_size in [32, 64, 128, 256]]
-
-        prompt = "Today is a sunny day and I like"
-        model_path = DEFAULT_SMALL_MODEL_NAME_FOR_TEST
-
-        sampling_params = {"temperature": 0, "max_new_tokens": 8}
-
-        for torchao_config in torchao_args_list:
-            engine = sgl.Engine(
-                model_path=model_path, random_seed=42, torchao_config=torchao_config
-            )
-            engine.generate(prompt, sampling_params)
-            engine.shutdown()
-
 
 if __name__ == "__main__":
     unittest.main()