[Misc] Make benchmarks use EngineArgs (#9529)

benchmarks/benchmark_throughput.py

@@ -1,5 +1,6 @@
 """Benchmark offline inference throughput."""
 import argparse
+import dataclasses
 import json
 import random
 import time
@@ -11,10 +12,9 @@ from tqdm import tqdm
 from transformers import (AutoModelForCausalLM, AutoTokenizer,
                           PreTrainedTokenizerBase)
 
-from vllm.engine.arg_utils import DEVICE_OPTIONS, AsyncEngineArgs, EngineArgs
+from vllm.engine.arg_utils import AsyncEngineArgs, EngineArgs
 from vllm.entrypoints.openai.api_server import (
     build_async_engine_client_from_engine_args)
-from vllm.model_executor.layers.quantization import QUANTIZATION_METHODS
 from vllm.sampling_params import BeamSearchParams
 from vllm.utils import FlexibleArgumentParser, merge_async_iterators
 
@@ -67,53 +67,11 @@ def sample_requests(
 
 def run_vllm(
     requests: List[Tuple[str, int, int]],
-    model: str,
-    tokenizer: str,
-    quantization: Optional[str],
-    tensor_parallel_size: int,
-    seed: int,
     n: int,
-    trust_remote_code: bool,
-    dtype: str,
-    max_model_len: Optional[int],
-    enforce_eager: bool,
-    kv_cache_dtype: str,
-    quantization_param_path: Optional[str],
-    device: str,
-    enable_prefix_caching: bool,
-    enable_chunked_prefill: bool,
-    max_num_batched_tokens: int,
-    distributed_executor_backend: Optional[str],
-    gpu_memory_utilization: float = 0.9,
-    num_scheduler_steps: int = 1,
-    download_dir: Optional[str] = None,
-    load_format: str = EngineArgs.load_format,
-    disable_async_output_proc: bool = False,
+    engine_args: EngineArgs,
 ) -> float:
     from vllm import LLM, SamplingParams
-    llm = LLM(
-        model=model,
-        tokenizer=tokenizer,
-        quantization=quantization,
-        tensor_parallel_size=tensor_parallel_size,
-        seed=seed,
-        trust_remote_code=trust_remote_code,
-        dtype=dtype,
-        max_model_len=max_model_len,
-        gpu_memory_utilization=gpu_memory_utilization,
-        enforce_eager=enforce_eager,
-        kv_cache_dtype=kv_cache_dtype,
-        quantization_param_path=quantization_param_path,
-        device=device,
-        enable_prefix_caching=enable_prefix_caching,
-        download_dir=download_dir,
-        enable_chunked_prefill=enable_chunked_prefill,
-        max_num_batched_tokens=max_num_batched_tokens,
-        distributed_executor_backend=distributed_executor_backend,
-        load_format=load_format,
-        num_scheduler_steps=num_scheduler_steps,
-        disable_async_output_proc=disable_async_output_proc,
-    )
+    llm = LLM(**dataclasses.asdict(engine_args))
 
     # Add the requests to the engine.
     prompts: List[str] = []
@@ -155,56 +113,11 @@ def run_vllm(
 
 async def run_vllm_async(
     requests: List[Tuple[str, int, int]],
-    model: str,
-    tokenizer: str,
-    quantization: Optional[str],
-    tensor_parallel_size: int,
-    seed: int,
     n: int,
-    trust_remote_code: bool,
-    dtype: str,
-    max_model_len: Optional[int],
-    enforce_eager: bool,
-    kv_cache_dtype: str,
-    quantization_param_path: Optional[str],
-    device: str,
-    enable_prefix_caching: bool,
-    enable_chunked_prefill: bool,
-    max_num_batched_tokens: int,
-    distributed_executor_backend: Optional[str],
-    gpu_memory_utilization: float = 0.9,
-    num_scheduler_steps: int = 1,
-    download_dir: Optional[str] = None,
-    load_format: str = EngineArgs.load_format,
-    disable_async_output_proc: bool = False,
+    engine_args: AsyncEngineArgs,
     disable_frontend_multiprocessing: bool = False,
 ) -> float:
     from vllm import SamplingParams
-    engine_args = AsyncEngineArgs(
-        model=model,
-        tokenizer=tokenizer,
-        quantization=quantization,
-        tensor_parallel_size=tensor_parallel_size,
-        seed=seed,
-        trust_remote_code=trust_remote_code,
-        dtype=dtype,
-        max_model_len=max_model_len,
-        gpu_memory_utilization=gpu_memory_utilization,
-        enforce_eager=enforce_eager,
-        kv_cache_dtype=kv_cache_dtype,
-        quantization_param_path=quantization_param_path,
-        device=device,
-        enable_prefix_caching=enable_prefix_caching,
-        download_dir=download_dir,
-        enable_chunked_prefill=enable_chunked_prefill,
-        max_num_batched_tokens=max_num_batched_tokens,
-        distributed_executor_backend=distributed_executor_backend,
-        load_format=load_format,
-        num_scheduler_steps=num_scheduler_steps,
-        disable_async_output_proc=disable_async_output_proc,
-        worker_use_ray=False,
-        disable_log_requests=True,
-    )
 
     async with build_async_engine_client_from_engine_args(
             engine_args, disable_frontend_multiprocessing) as llm:
@@ -328,23 +241,17 @@ def main(args: argparse.Namespace):
                                    args.output_len)
 
     if args.backend == "vllm":
-        run_args = [
-            requests, args.model, args.tokenizer, args.quantization,
-            args.tensor_parallel_size, args.seed, args.n,
-            args.trust_remote_code, args.dtype, args.max_model_len,
-            args.enforce_eager, args.kv_cache_dtype,
-            args.quantization_param_path, args.device,
-            args.enable_prefix_caching, args.enable_chunked_prefill,
-            args.max_num_batched_tokens, args.distributed_executor_backend,
-            args.gpu_memory_utilization, args.num_scheduler_steps,
-            args.download_dir, args.load_format, args.disable_async_output_proc
-        ]
-
         if args.async_engine:
-            run_args.append(args.disable_frontend_multiprocessing)
-            elapsed_time = uvloop.run(run_vllm_async(*run_args))
+            elapsed_time = uvloop.run(
+                run_vllm_async(
+                    requests,
+                    args.n,
+                    AsyncEngineArgs.from_cli_args(args),
+                    args.disable_frontend_multiprocessing,
+                ))
         else:
-            elapsed_time = run_vllm(*run_args)
+            elapsed_time = run_vllm(requests, args.n,
+                                    EngineArgs.from_cli_args(args))
     elif args.backend == "hf":
         assert args.tensor_parallel_size == 1
         elapsed_time = run_hf(requests, args.model, tokenizer, args.n,
@@ -391,13 +298,6 @@ if __name__ == "__main__":
                         default=None,
                         help="Output length for each request. Overrides the "
                         "output length from the dataset.")
-    parser.add_argument("--model", type=str, default="facebook/opt-125m")
-    parser.add_argument("--tokenizer", type=str, default=None)
-    parser.add_argument('--quantization',
-                        '-q',
-                        choices=[*QUANTIZATION_METHODS, None],
-                        default=None)
-    parser.add_argument("--tensor-parallel-size", "-tp", type=int, default=1)
     parser.add_argument("--n",
                         type=int,
                         default=1,
@@ -406,123 +306,15 @@ if __name__ == "__main__":
                         type=int,
                         default=1000,
                         help="Number of prompts to process.")
-    parser.add_argument("--seed", type=int, default=0)
     parser.add_argument("--hf-max-batch-size",
                         type=int,
                         default=None,
                         help="Maximum batch size for HF backend.")
-    parser.add_argument('--trust-remote-code',
-                        action='store_true',
-                        help='trust remote code from huggingface')
-    parser.add_argument(
-        '--max-model-len',
-        type=int,
-        default=None,
-        help='Maximum length of a sequence (including prompt and output). '
-        'If None, will be derived from the model.')
-    parser.add_argument(
-        '--dtype',
-        type=str,
-        default='auto',
-        choices=['auto', 'half', 'float16', 'bfloat16', 'float', 'float32'],
-        help='data type for model weights and activations. '
-        'The "auto" option will use FP16 precision '
-        'for FP32 and FP16 models, and BF16 precision '
-        'for BF16 models.')
-    parser.add_argument('--gpu-memory-utilization',
-                        type=float,
-                        default=0.9,
-                        help='the fraction of GPU memory to be used for '
-                        'the model executor, which can range from 0 to 1.'
-                        'If unspecified, will use the default value of 0.9.')
-    parser.add_argument("--enforce-eager",
-                        action="store_true",
-                        help="enforce eager execution")
-    parser.add_argument(
-        '--kv-cache-dtype',
-        type=str,
-        choices=['auto', 'fp8', 'fp8_e5m2', 'fp8_e4m3'],
-        default="auto",
-        help='Data type for kv cache storage. If "auto", will use model '
-        'data type. CUDA 11.8+ supports fp8 (=fp8_e4m3) and fp8_e5m2. '
-        'ROCm (AMD GPU) supports fp8 (=fp8_e4m3)')
-    parser.add_argument(
-        '--quantization-param-path',
-        type=str,
-        default=None,
-        help='Path to the JSON file containing the KV cache scaling factors. '
-        'This should generally be supplied, when KV cache dtype is FP8. '
-        'Otherwise, KV cache scaling factors default to 1.0, which may cause '
-        'accuracy issues. FP8_E5M2 (without scaling) is only supported on '
-        'cuda version greater than 11.8. On ROCm (AMD GPU), FP8_E4M3 is '
-        'instead supported for common inference criteria.')
-    parser.add_argument("--device",
-                        type=str,
-                        default="auto",
-                        choices=DEVICE_OPTIONS,
-                        help='device type for vLLM execution')
-    parser.add_argument(
-        "--num-scheduler-steps",
-        type=int,
-        default=1,
-        help="Maximum number of forward steps per scheduler call.")
-    parser.add_argument(
-        "--enable-prefix-caching",
-        action='store_true',
-        help="Enable automatic prefix caching for vLLM backend.")
-    parser.add_argument("--enable-chunked-prefill",
-                        action='store_true',
-                        help="enable chunked prefill for vLLM backend.")
-    parser.add_argument('--max-num-batched-tokens',
-                        type=int,
-                        default=None,
-                        help='maximum number of batched tokens per '
-                        'iteration')
-    parser.add_argument('--download-dir',
-                        type=str,
-                        default=None,
-                        help='directory to download and load the weights, '
-                        'default to the default cache dir of huggingface')
     parser.add_argument(
         '--output-json',
         type=str,
         default=None,
         help='Path to save the throughput results in JSON format.')
-    parser.add_argument(
-        '--distributed-executor-backend',
-        choices=['ray', 'mp'],
-        default=None,
-        help='Backend to use for distributed serving. When more than 1 GPU '
-        'is used, will be automatically set to "ray" if installed '
-        'or "mp" (multiprocessing) otherwise.')
-    parser.add_argument(
-        '--load-format',
-        type=str,
-        default=EngineArgs.load_format,
-        choices=[
-            'auto', 'pt', 'safetensors', 'npcache', 'dummy', 'tensorizer',
-            'bitsandbytes'
-        ],
-        help='The format of the model weights to load.\n\n'
-        '* "auto" will try to load the weights in the safetensors format '
-        'and fall back to the pytorch bin format if safetensors format '
-        'is not available.\n'
-        '* "pt" will load the weights in the pytorch bin format.\n'
-        '* "safetensors" will load the weights in the safetensors format.\n'
-        '* "npcache" will load the weights in pytorch format and store '
-        'a numpy cache to speed up the loading.\n'
-        '* "dummy" will initialize the weights with random values, '
-        'which is mainly for profiling.\n'
-        '* "tensorizer" will load the weights using tensorizer from '
-        'CoreWeave. See the Tensorize vLLM Model script in the Examples'
-        'section for more information.\n'
-        '* "bitsandbytes" will load the weights using bitsandbytes '
-        'quantization.\n')
-    parser.add_argument(
-        "--disable-async-output-proc",
-        action='store_true',
-        default=False,
-        help="Disable async output processor for vLLM backend.")
     parser.add_argument("--async-engine",
                         action='store_true',
                         default=False,
@@ -531,6 +323,7 @@ if __name__ == "__main__":
                         action='store_true',
                         default=False,
                         help="Disable decoupled async engine frontend.")
+    parser = AsyncEngineArgs.add_cli_args(parser)
     args = parser.parse_args()
     if args.tokenizer is None:
         args.tokenizer = args.model