Fix a draft model accuracy bug in eagle; support step=1; return logprob in eagle (#4134)

Co-authored-by: Sehoon Kim <kssteven418@gmail.com>
Co-authored-by: SangBin Cho <rkooo567@gmail.com>
Co-authored-by: Sehoon Kim <sehoon@x.ai>

test/srt/test_gptqmodel_dynamic.py

@@ -143,11 +143,11 @@ class TestGPTQModelDynamic(unittest.TestCase):
 
         print(f"result = `{result}`")
 
-        assert "paris" in result["text"].lower()
+        self.assertIn("paris", result["text"].lower())
 
         throughput = max_tokens / (tok - tic)
         print(f"Throughput: {throughput} tokens/s")
-        assert throughput >= 140
+        self.assertGreaterEqual(throughput, 140)
 
     def test_gptq_module(self):
         check_quant_method(self.MODEL_PATH, use_marlin_kernel=False)