benchmark_throughput.py

"""Benchmark offline inference throughput."""
import argparse
import dataclasses
import json
import random
import time
from typing import List, Optional, Tuple

import torch
import uvloop
from tqdm import tqdm
from transformers import (AutoModelForCausalLM, AutoTokenizer,
                          PreTrainedTokenizerBase)

from vllm.engine.arg_utils import AsyncEngineArgs, EngineArgs
from vllm.entrypoints.openai.api_server import (
    build_async_engine_client_from_engine_args)
from vllm.sampling_params import BeamSearchParams
from vllm.utils import FlexibleArgumentParser, merge_async_iterators


def sample_requests(
    dataset_path: str,
    num_requests: int,
    tokenizer: PreTrainedTokenizerBase,
    fixed_output_len: Optional[int],
) -> List[Tuple[str, int, int]]:
    if fixed_output_len is not None and fixed_output_len < 4:
        raise ValueError("output_len too small")

    # Load the dataset.
    with open(dataset_path) as f:
        dataset = json.load(f)
    # Filter out the conversations with less than 2 turns.
    dataset = [data for data in dataset if len(data["conversations"]) >= 2]
    # Only keep the first two turns of each conversation.
    dataset = [(data["conversations"][0]["value"],
                data["conversations"][1]["value"]) for data in dataset]

    # Shuffle the dataset.
    random.shuffle(dataset)

    # Filter out sequences that are too long or too short
    filtered_dataset: List[Tuple[str, int, int]] = []
    for i in range(len(dataset)):
        if len(filtered_dataset) == num_requests:
            break

        # Tokenize the prompts and completions.
        prompt = dataset[i][0]
        prompt_token_ids = tokenizer(prompt).input_ids
        completion = dataset[i][1]
        completion_token_ids = tokenizer(completion).input_ids
        prompt_len = len(prompt_token_ids)
        output_len = len(completion_token_ids
                         ) if fixed_output_len is None else fixed_output_len
        if prompt_len < 4 or output_len < 4:
            # Prune too short sequences.
            continue
        if prompt_len > 1024 or prompt_len + output_len > 2048:
            # Prune too long sequences.
            continue
        filtered_dataset.append((prompt, prompt_len, output_len))

    return filtered_dataset


def run_vllm(
    requests: List[Tuple[str, int, int]],
    n: int,
    engine_args: EngineArgs,
) -> float:
    from vllm import LLM, SamplingParams
    llm = LLM(**dataclasses.asdict(engine_args))

    # Add the requests to the engine.
    prompts: List[str] = []
    sampling_params: List[SamplingParams] = []
    for prompt, _, output_len in requests:
        prompts.append(prompt)
        sampling_params.append(
            SamplingParams(
                n=n,
                temperature=1.0,
                top_p=1.0,
                ignore_eos=True,
                max_tokens=output_len,
            ))

    use_beam_search = False

    if not use_beam_search:
        start = time.perf_counter()
        llm.generate(prompts, sampling_params, use_tqdm=True)
        end = time.perf_counter()
    else:
        prompts = [prompt for prompt, _, _ in requests]
        # output_len should be the same for all requests.
        output_len = requests[0][2]
        for prompt, input_len, _output_len in requests:
            assert _output_len == output_len
        start = time.perf_counter()
        llm.beam_search(
            prompts,
            BeamSearchParams(
                beam_width=n,
                max_tokens=output_len,
                ignore_eos=True,
            ))
        end = time.perf_counter()
    return end - start


async def run_vllm_async(
    requests: List[Tuple[str, int, int]],
    n: int,
    engine_args: AsyncEngineArgs,
    disable_frontend_multiprocessing: bool = False,
) -> float:
    from vllm import SamplingParams

    async with build_async_engine_client_from_engine_args(
            engine_args, disable_frontend_multiprocessing) as llm:

        # Add the requests to the engine.
        prompts: List[str] = []
        sampling_params: List[SamplingParams] = []
        for prompt, _, output_len in requests:
            prompts.append(prompt)
            sampling_params.append(
                SamplingParams(
                    n=n,
                    temperature=1.0,
                    top_p=1.0,
                    ignore_eos=True,
                    max_tokens=output_len,
                ))

        generators = []
        start = time.perf_counter()
        for i, (prompt, sp) in enumerate(zip(prompts, sampling_params)):
            generator = llm.generate(prompt, sp, request_id=f"test{i}")
            generators.append(generator)
        all_gens = merge_async_iterators(*generators)
        async for i, res in all_gens:
            pass
        end = time.perf_counter()
        return end - start


def run_hf(
    requests: List[Tuple[str, int, int]],
    model: str,
    tokenizer: PreTrainedTokenizerBase,
    n: int,
    max_batch_size: int,
    trust_remote_code: bool,
) -> float:
    llm = AutoModelForCausalLM.from_pretrained(
        model, torch_dtype=torch.float16, trust_remote_code=trust_remote_code)
    if llm.config.model_type == "llama":
        # To enable padding in the HF backend.
        tokenizer.pad_token = tokenizer.eos_token
    llm = llm.cuda()

    pbar = tqdm(total=len(requests))
    start = time.perf_counter()
    batch: List[str] = []
    max_prompt_len = 0
    max_output_len = 0
    for i in range(len(requests)):
        prompt, prompt_len, output_len = requests[i]
        # Add the prompt to the batch.
        batch.append(prompt)
        max_prompt_len = max(max_prompt_len, prompt_len)
        max_output_len = max(max_output_len, output_len)
        if len(batch) < max_batch_size and i != len(requests) - 1:
            # Check if we can add more requests to the batch.
            _, next_prompt_len, next_output_len = requests[i + 1]
            if (max(max_prompt_len, next_prompt_len) +
                    max(max_output_len, next_output_len)) <= 2048:
                # We can add more requests to the batch.
                continue

        # Generate the sequences.
        input_ids = tokenizer(batch, return_tensors="pt",
                              padding=True).input_ids
        llm_outputs = llm.generate(
            input_ids=input_ids.cuda(),
            do_sample=True,
            num_return_sequences=n,
            temperature=1.0,
            top_p=1.0,
            use_cache=True,
            max_new_tokens=max_output_len,
        )
        # Include the decoding time.
        tokenizer.batch_decode(llm_outputs, skip_special_tokens=True)
        pbar.update(len(batch))

        # Clear the batch.
        batch = []
        max_prompt_len = 0
        max_output_len = 0
    end = time.perf_counter()
    return end - start


def run_mii(
    requests: List[Tuple[str, int, int]],
    model: str,
    tensor_parallel_size: int,
    output_len: int,
) -> float:
    from mii import client, serve
    llm = serve(model, tensor_parallel=tensor_parallel_size)
    prompts = [prompt for prompt, _, _ in requests]

    start = time.perf_counter()
    llm.generate(prompts, max_new_tokens=output_len)
    end = time.perf_counter()
    client = client(model)
    client.terminate_server()
    return end - start


def main(args: argparse.Namespace):
    print(args)
    random.seed(args.seed)

    # Sample the requests.
    tokenizer = AutoTokenizer.from_pretrained(
        args.tokenizer, trust_remote_code=args.trust_remote_code)
    if args.dataset is None:
        # Synthesize a prompt with the given input length.
        # As tokenizer may add additional tokens like BOS, we need to try
        # different lengths to get the desired input length.
        for i in range(-10, 10):
            prompt = "hi " * (args.input_len + i)
            tokenized_prompt = tokenizer(prompt).input_ids
            if len(tokenized_prompt) == args.input_len:
                break
        else:
            raise ValueError(
                f"Failed to synthesize a prompt with {args.input_len} tokens.")
        requests = [(prompt, args.input_len, args.output_len)
                    for _ in range(args.num_prompts)]
    else:
        requests = sample_requests(args.dataset, args.num_prompts, tokenizer,
                                   args.output_len)

    if args.backend == "vllm":
        if args.async_engine:
            elapsed_time = uvloop.run(
                run_vllm_async(
                    requests,
                    args.n,
                    AsyncEngineArgs.from_cli_args(args),
                    args.disable_frontend_multiprocessing,
                ))
        else:
            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,
                              args.hf_max_batch_size, args.trust_remote_code)
    elif args.backend == "mii":
        elapsed_time = run_mii(requests, args.model, args.tensor_parallel_size,
                               args.output_len)
    else:
        raise ValueError(f"Unknown backend: {args.backend}")
    total_num_tokens = sum(prompt_len + output_len
                           for _, prompt_len, output_len in requests)
    total_output_tokens = sum(output_len for _, _, output_len in requests)
    print(f"Throughput: {len(requests) / elapsed_time:.2f} requests/s, "
          f"{total_num_tokens / elapsed_time:.2f} total tokens/s, "
          f"{total_output_tokens / elapsed_time:.2f} output tokens/s")

    # Output JSON results if specified
    if args.output_json:
        results = {
            "elapsed_time": elapsed_time,
            "num_requests": len(requests),
            "total_num_tokens": total_num_tokens,
            "requests_per_second": len(requests) / elapsed_time,
            "tokens_per_second": total_num_tokens / elapsed_time,
        }
        with open(args.output_json, "w") as f:
            json.dump(results, f, indent=4)


if __name__ == "__main__":
    parser = FlexibleArgumentParser(description="Benchmark the throughput.")
    parser.add_argument("--backend",
                        type=str,
                        choices=["vllm", "hf", "mii"],
                        default="vllm")
    parser.add_argument("--dataset",
                        type=str,
                        default=None,
                        help="Path to the dataset.")
    parser.add_argument("--input-len",
                        type=int,
                        default=None,
                        help="Input prompt length for each request")
    parser.add_argument("--output-len",
                        type=int,
                        default=None,
                        help="Output length for each request. Overrides the "
                        "output length from the dataset.")
    parser.add_argument("--n",
                        type=int,
                        default=1,
                        help="Number of generated sequences per prompt.")
    parser.add_argument("--num-prompts",
                        type=int,
                        default=1000,
                        help="Number of prompts to process.")
    parser.add_argument("--hf-max-batch-size",
                        type=int,
                        default=None,
                        help="Maximum batch size for HF backend.")
    parser.add_argument(
        '--output-json',
        type=str,
        default=None,
        help='Path to save the throughput results in JSON format.')
    parser.add_argument("--async-engine",
                        action='store_true',
                        default=False,
                        help="Use vLLM async engine rather than LLM class.")
    parser.add_argument("--disable-frontend-multiprocessing",
                        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
    if args.dataset is None:
        assert args.input_len is not None
        assert args.output_len is not None
    else:
        assert args.input_len is None

    if args.backend == "vllm":
        if args.hf_max_batch_size is not None:
            raise ValueError("HF max batch size is only for HF backend.")
    elif args.backend == "hf":
        if args.hf_max_batch_size is None:
            raise ValueError("HF max batch size is required for HF backend.")
        if args.quantization is not None:
            raise ValueError("Quantization is only for vLLM backend.")
    elif args.backend == "mii":
        if args.dtype != "auto":
            raise ValueError("dtype must be auto for MII backend.")
        if args.n != 1:
            raise ValueError("n must be 1 for MII backend.")
        if args.quantization is not None:
            raise ValueError("Quantization is only for vLLM backend.")
        if args.hf_max_batch_size is not None:
            raise ValueError("HF max batch size is only for HF backend.")
        if args.tokenizer != args.model:
            raise ValueError("Tokenizer must be the same as the model for MII "
                             "backend.")
    main(args)