[Bugfix] Fix benchmark script bug: inaccurate stats for vllm backend when...

[Bugfix] Fix benchmark script bug: inaccurate stats for vllm backend when max_model_len < input_len + output_len (#13691)
Signed-off-by: WangErXiao <863579016@qq.com>

benchmarks/benchmark_guided.py

@@ -46,6 +46,12 @@ def run_vllm(requests: List[SampleRequest],
              warmup: bool = False) -> float:
     from vllm import LLM, SamplingParams
     llm = LLM(**vars(engine_args))
+    assert all(
+        llm.llm_engine.model_config.max_model_len >= (
+            request.prompt_len + request.expected_output_len)
+        for request in requests), (
+            "Please ensure that max_model_len is greater than the sum of"
+            " prompt_len and expected_output_len for all requests.")
 
     # Add the requests to the engine.
     prompts: List[str] = []
@@ -115,6 +121,13 @@ async def run_vllm_async(
     async with build_async_engine_client_from_engine_args(
             engine_args, disable_frontend_multiprocessing) as llm:
 
+        assert all(
+            llm.model_config.max_model_len >= (request.prompt_len +
+                                               request.expected_output_len)
+            for request in requests), (
+                "Please ensure that max_model_len is greater than the sum of"
+                " prompt_len and expected_output_len for all requests.")
+
         # Add the requests to the engine.
         prompts: List[str] = []
         sampling_params: List[SamplingParams] = []

benchmarks/benchmark_latency.py

@@ -42,6 +42,10 @@ def main(args: argparse.Namespace):
     # NOTE(woosuk): If the request cannot be processed in a single batch,
     # the engine will automatically process the request in multiple batches.
     llm = LLM(**dataclasses.asdict(engine_args))
+    assert llm.llm_engine.model_config.max_model_len >= (
+        args.input_len + args.output_len), (
+            "Please ensure that max_model_len is greater than"
+            " the sum of input_len and output_len.")
 
     sampling_params = SamplingParams(
         n=args.n,

benchmarks/benchmark_prioritization.py

@@ -13,6 +13,11 @@ from vllm.engine.arg_utils import EngineArgs
 from vllm.utils import FlexibleArgumentParser
 
 
+#Select a equi-probable random priority
+def get_random_flag():
+    return 0 if random.random() < 0.5 else 1
+
+
 def sample_requests(
     dataset_path: str,
     num_requests: int,
@@ -55,8 +60,7 @@ def sample_requests(
             # Prune too long sequences.
             continue
 
-        #Select a equi-probable random priority
-        priority = 0 if random.random() < 0.5 else 1
+        priority = get_random_flag()
 
         filtered_dataset.append((prompt, prompt_len, output_len, priority))
 
@@ -71,6 +75,12 @@ def run_vllm(
     from vllm import LLM, SamplingParams
     llm = LLM(**dataclasses.asdict(engine_args))
 
+    assert all(
+        llm.llm_engine.model_config.max_model_len >= (request[1] + request[2])
+        for request in requests), (
+            "Please ensure that max_model_len is greater than the sum of"
+            " input_len and output_len for all requests.")
+
     # Add the requests to the engine.
     prompts = []
     sampling_params = []
@@ -103,8 +113,8 @@ def main(args: argparse.Namespace):
     if args.dataset is None:
         # Synthesize a prompt with the given input length.
         prompt = "hi" * (args.input_len - 1)
-        requests = [(prompt, args.input_len, args.output_len)
-                    for _ in range(args.num_prompts)]
+        requests = [(prompt, args.input_len, args.output_len,
+                     get_random_flag()) for _ in range(args.num_prompts)]
     else:
         requests = sample_requests(args.dataset, args.num_prompts, tokenizer,
                                    args.output_len)

benchmarks/benchmark_throughput.py

@@ -171,7 +171,12 @@ def run_vllm(
 ) -> float:
     from vllm import LLM, SamplingParams
     llm = LLM(**dataclasses.asdict(engine_args))
-
+    assert all(
+        llm.llm_engine.model_config.max_model_len >= (
+            request.prompt_len + request.expected_output_len)
+        for request in requests), (
+            "Please ensure that max_model_len is greater than the sum of"
+            " prompt_len and expected_output_len for all requests.")
     # Add the requests to the engine.
     prompts: List[TextPrompt] = []
     sampling_params: List[SamplingParams] = []
@@ -229,6 +234,12 @@ async def run_vllm_async(
 
     async with build_async_engine_client_from_engine_args(
             engine_args, disable_frontend_multiprocessing) as llm:
+        assert all(
+            llm.model_config.max_model_len >= (request.prompt_len +
+                                               request.expected_output_len)
+            for request in requests), (
+                "Please ensure that max_model_len is greater than the sum of"
+                " prompt_len and expected_output_len for all requests.")
 
         # Add the requests to the engine.
         prompts: List[TextPrompt] = []