[FIX] Fix styles in automatic prefix caching & add a automatic prefix caching benchmark (#3158)

benchmarks/benchmark_prefix_caching.py

@@ -0,0 +1,59 @@
+import argparse
+import time
+
+from vllm import LLM
+from vllm import SamplingParams
+
+PROMPT = "You are a helpful assistant in recognizes the content of tables in markdown format. Here is a table as fellows. You need to answer my question about the table.\n# Table\n|Opening|Opening|Sl. No.|Film|Cast|Director|Music Director|Notes|\n|----|----|----|----|----|----|----|----|\n|J A N|9|1|Agni Pushpam|Jayabharathi, Kamalahasan|Jeassy|M. K. Arjunan||\n|J A N|16|2|Priyamvada|Mohan Sharma, Lakshmi, KPAC Lalitha|K. S. Sethumadhavan|V. Dakshinamoorthy||\n|J A N|23|3|Yakshagaanam|Madhu, Sheela|Sheela|M. S. Viswanathan||\n|J A N|30|4|Paalkkadal|Sheela, Sharada|T. K. Prasad|A. T. Ummer||\n|F E B|5|5|Amma|Madhu, Srividya|M. Krishnan Nair|M. K. Arjunan||\n|F E B|13|6|Appooppan|Thikkurissi Sukumaran Nair, Kamal Haasan|P. Bhaskaran|M. S. Baburaj||\n|F E B|20|7|Srishti|Chowalloor Krishnankutty, Ravi Alummoodu|K. T. Muhammad|M. S. Baburaj||\n|F E B|20|8|Vanadevatha|Prem Nazir, Madhubala|Yusufali Kechery|G. Devarajan||\n|F E B|27|9|Samasya|Madhu, Kamalahaasan|K. Thankappan|Shyam||\n|F E B|27|10|Yudhabhoomi|K. P. Ummer, Vidhubala|Crossbelt Mani|R. K. Shekhar||\n|M A R|5|11|Seemantha Puthran|Prem Nazir, Jayabharathi|A. B. Raj|M. K. Arjunan||\n|M A R|12|12|Swapnadanam|Rani Chandra, Dr. Mohandas|K. G. George|Bhaskar Chandavarkar||\n|M A R|19|13|Thulavarsham|Prem Nazir, sreedevi, Sudheer|N. Sankaran Nair|V. Dakshinamoorthy||\n|M A R|20|14|Aruthu|Kaviyoor Ponnamma, Kamalahasan|Ravi|G. Devarajan||\n|M A R|26|15|Swimming Pool|Kamal Haasan, M. G. Soman|J. Sasikumar|M. K. Arjunan||\n\n# Question\nWhat' s the content in the (1,1) cells\n"
+
+
+def test_prefix(llm=None, sampling_params=None, prompts=None, prefix_len=None):
+    start_time = time.time()
+    # whether use Prefix
+    if prefix_len != None:
+        # start inference
+        llm.generate(prompts,
+                     sampling_params=sampling_params,
+                     prefix_pos=prefix_len)
+    else:
+        llm.generate(prompts, sampling_params=sampling_params)
+
+    end_time = time.time()
+    print(f"cost time {end_time - start_time}")
+
+
+def main(args):
+    llm = LLM(model="baichuan-inc/Baichuan2-13B-Chat",
+              tokenizer_mode='auto',
+              trust_remote_code=True,
+              enforce_eager=True,
+              enable_prefix_caching=args.enable_prefix_caching)
+
+    num_prompts = 100
+    prompts = [PROMPT] * num_prompts
+    sampling_params = SamplingParams(temperature=0, max_tokens=100)
+
+    print("------warm up------")
+    test_prefix(
+        llm=llm,
+        prompts=prompts[:1],
+        sampling_params=sampling_params,
+    )
+
+    print("------start generating------")
+    test_prefix(
+        llm=llm,
+        prompts=prompts,
+        sampling_params=sampling_params,
+    )
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser(
+        description='Benchmark the performance with or without automatic '
+        'prefix caching.')
+    parser.add_argument('--enable-prefix-caching',
+                        action='store_true',
+                        help='enable prefix caching')
+    args = parser.parse_args()
+    main(args)

benchmarks/benchmark_throughput.py

@@ -303,7 +303,10 @@ if __name__ == "__main__":
         default="cuda",
         choices=["cuda"],
         help='device type for vLLM execution, supporting CUDA only currently.')
-    parser.add_argument("--enable_prefix_caching", action='store_true')
+    parser.add_argument(
+        "--enable-prefix-caching",
+        action='store_true',
+        help="enable automatic prefix caching for vLLM backend.")
     args = parser.parse_args()
     if args.tokenizer is None:
         args.tokenizer = args.model