This commit is contained in:
2025-08-13 19:46:19 +08:00
commit 5d2e7edf78
1232 changed files with 361215 additions and 0 deletions

0
benchmarks/__init__.py Normal file
View File

1185
benchmarks/datasets.py Normal file

File diff suppressed because it is too large Load Diff

View File

@@ -0,0 +1,381 @@
# SPDX-License-Identifier: Apache-2.0
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
"""The request function for API endpoints."""
import io
import json
import os
import sys
import time
import traceback
from dataclasses import dataclass, field
from typing import Optional
import aiohttp
from tqdm.asyncio import tqdm
AIOHTTP_TIMEOUT = aiohttp.ClientTimeout(total=6 * 60 * 60)
@dataclass
class RequestFuncInput:
"""The input for the request function."""
prompt: str
api_url: str
prompt_len: int
output_len: int
model: str
model_name: Optional[str] = None
logprobs: Optional[int] = None
extra_body: Optional[dict] = None
multi_modal_content: Optional[dict] = None
ignore_eos: bool = False
language: Optional[str] = None
@dataclass
class RequestFuncOutput:
"""The output of the request function including metrics."""
generated_text: str = ""
success: bool = False
latency: float = 0.0
output_tokens: int = 0
ttft: float = 0.0 # Time to first token
itl: list[float] = field(
default_factory=list) # list of inter-token latencies
tpot: float = 0.0 # avg next-token latencies
prompt_len: int = 0
error: str = ""
async def async_request_openai_completions(
request_func_input: RequestFuncInput,
pbar: Optional[tqdm] = None,
) -> RequestFuncOutput:
"""The async request function for the OpenAI Completions API.
Args:
request_func_input: The input for the request function.
pbar: The progress bar to display the progress.
Returns:
The output of the request function.
"""
api_url = request_func_input.api_url
assert api_url.endswith(
("completions", "profile")
), "OpenAI Completions API URL must end with 'completions' or 'profile'."
async with aiohttp.ClientSession(trust_env=True,
timeout=AIOHTTP_TIMEOUT) as session:
payload = {
"model": request_func_input.model_name \
if request_func_input.model_name else request_func_input.model,
"prompt": request_func_input.prompt,
"temperature": 0.0,
"repetition_penalty": 1.0,
"max_tokens": request_func_input.output_len,
"logprobs": request_func_input.logprobs,
"stream": True,
"stream_options": {
"include_usage": True,
},
}
if request_func_input.ignore_eos:
payload["ignore_eos"] = request_func_input.ignore_eos
if request_func_input.extra_body:
payload.update(request_func_input.extra_body)
headers = {
"Authorization": f"Bearer {os.environ.get('OPENAI_API_KEY')}"
}
output = RequestFuncOutput()
output.prompt_len = request_func_input.prompt_len
generated_text = ""
st = time.perf_counter()
most_recent_timestamp = st
try:
async with session.post(url=api_url, json=payload,
headers=headers) as response:
if response.status == 200:
first_chunk_received = False
async for chunk_bytes in response.content:
chunk_bytes = chunk_bytes.strip()
if not chunk_bytes:
continue
chunk = chunk_bytes.decode("utf-8").removeprefix(
"data: ")
if chunk != "[DONE]":
data = json.loads(chunk)
# NOTE: Some completion API might have a last
# usage summary response without a token so we
# want to check a token was generated
if choices := data.get("choices"):
# Note that text could be empty here
# e.g. for special tokens
text = choices[0].get("text")
timestamp = time.perf_counter()
# First token
if not first_chunk_received:
first_chunk_received = True
ttft = time.perf_counter() - st
output.ttft = ttft
# Decoding phase
else:
output.itl.append(timestamp -
most_recent_timestamp)
most_recent_timestamp = timestamp
generated_text += text or ""
elif usage := data.get("usage"):
output.output_tokens = usage.get(
"completion_tokens")
if first_chunk_received:
output.success = True
else:
output.success = False
output.error = (
"Never received a valid chunk to calculate TTFT."
"This response will be marked as failed!")
output.generated_text = generated_text
output.latency = most_recent_timestamp - st
else:
output.error = response.reason or ""
output.success = False
except Exception:
output.success = False
exc_info = sys.exc_info()
output.error = "".join(traceback.format_exception(*exc_info))
if pbar:
pbar.update(1)
return output
async def async_request_openai_chat_completions(
request_func_input: RequestFuncInput,
pbar: Optional[tqdm] = None,
) -> RequestFuncOutput:
api_url = request_func_input.api_url
assert api_url.endswith(("chat/completions", "profile")), (
"OpenAI Chat Completions API URL must end with 'chat/completions'.")
async with aiohttp.ClientSession(trust_env=True,
timeout=AIOHTTP_TIMEOUT) as session:
content = [{"type": "text", "text": request_func_input.prompt}]
if request_func_input.multi_modal_content:
content.append(request_func_input.multi_modal_content)
payload = {
"model":
request_func_input.model_name
if request_func_input.model_name else request_func_input.model,
"messages": [
{
"role": "user",
"content": content
},
],
"temperature":
0.0,
"max_completion_tokens":
request_func_input.output_len,
"stream":
True,
"stream_options": {
"include_usage": True,
},
}
if request_func_input.ignore_eos:
payload["ignore_eos"] = request_func_input.ignore_eos
if request_func_input.extra_body:
payload.update(request_func_input.extra_body)
headers = {
"Content-Type": "application/json",
"Authorization": f"Bearer {os.environ.get('OPENAI_API_KEY')}",
}
output = RequestFuncOutput()
output.prompt_len = request_func_input.prompt_len
generated_text = ""
ttft = 0.0
st = time.perf_counter()
most_recent_timestamp = st
try:
async with session.post(url=api_url, json=payload,
headers=headers) as response:
if response.status == 200:
async for chunk_bytes in response.content:
chunk_bytes = chunk_bytes.strip()
if not chunk_bytes:
continue
chunk = chunk_bytes.decode("utf-8").removeprefix(
"data: ")
if chunk != "[DONE]":
timestamp = time.perf_counter()
data = json.loads(chunk)
if choices := data.get("choices"):
content = choices[0]["delta"].get("content")
# First token
if ttft == 0.0:
ttft = timestamp - st
output.ttft = ttft
# Decoding phase
else:
output.itl.append(timestamp -
most_recent_timestamp)
generated_text += content or ""
elif usage := data.get("usage"):
output.output_tokens = usage.get(
"completion_tokens")
most_recent_timestamp = timestamp
output.generated_text = generated_text
output.success = True
output.latency = most_recent_timestamp - st
else:
output.error = response.reason or ""
output.success = False
except Exception:
output.success = False
exc_info = sys.exc_info()
output.error = "".join(traceback.format_exception(*exc_info))
if pbar:
pbar.update(1)
return output
async def async_request_openai_audio(
request_func_input: RequestFuncInput,
pbar: Optional[tqdm] = None,
) -> RequestFuncOutput:
# Lazy import without PlaceholderModule to avoid vllm dep.
import soundfile
api_url = request_func_input.api_url
assert api_url.endswith(("transcriptions", "translations")), (
"OpenAI Chat Completions API URL must end with 'transcriptions' ")
"or `translations`."
async with aiohttp.ClientSession(trust_env=True,
timeout=AIOHTTP_TIMEOUT) as session:
content = [{"type": "text", "text": request_func_input.prompt}]
payload = {
"model":
request_func_input.model_name
if request_func_input.model_name else request_func_input.model,
"temperature":
0.0,
"max_completion_tokens":
request_func_input.output_len,
"stream":
True,
"language":
"en",
# Flattened due to multipart/form-data
"stream_include_usage":
True,
"stream_continuous_usage_stats":
True,
}
if request_func_input.extra_body:
payload.update(request_func_input.extra_body)
headers = {
"Authorization": f"Bearer {os.environ.get('OPENAI_API_KEY')}",
}
# Send audio file
def to_bytes(y, sr):
buffer = io.BytesIO()
soundfile.write(buffer, y, sr, format="WAV")
buffer.seek(0)
return buffer
with to_bytes(*request_func_input.multi_modal_content["audio"]) as f:
form = aiohttp.FormData()
form.add_field("file", f, content_type="audio/wav")
for key, value in payload.items():
form.add_field(key, str(value))
output = RequestFuncOutput()
output.prompt_len = request_func_input.prompt_len
generated_text = ""
ttft = 0.0
st = time.perf_counter()
most_recent_timestamp = st
try:
async with session.post(url=api_url,
data=form,
headers=headers) as response:
if response.status == 200:
async for chunk_bytes in response.content:
chunk_bytes = chunk_bytes.strip()
if not chunk_bytes:
continue
chunk = chunk_bytes.decode("utf-8").removeprefix(
"data: ")
if chunk != "[DONE]":
timestamp = time.perf_counter()
data = json.loads(chunk)
if choices := data.get("choices"):
content = choices[0]["delta"].get(
"content")
# First token
if ttft == 0.0:
ttft = timestamp - st
output.ttft = ttft
# Decoding phase
else:
output.itl.append(
timestamp - most_recent_timestamp)
generated_text += content or ""
elif usage := data.get("usage"):
output.output_tokens = usage.get(
"completion_tokens")
most_recent_timestamp = timestamp
output.generated_text = generated_text
output.success = True
output.latency = most_recent_timestamp - st
else:
output.error = response.reason or ""
output.success = False
except Exception:
output.success = False
exc_info = sys.exc_info()
output.error = "".join(traceback.format_exception(*exc_info))
if pbar:
pbar.update(1)
return output
# TODO: Add more request functions for different API protocols.
ASYNC_REQUEST_FUNCS = {
"vllm": async_request_openai_completions,
"openai": async_request_openai_completions,
"openai-chat": async_request_openai_chat_completions,
"openai-audio": async_request_openai_audio,
}
OPENAI_COMPATIBLE_BACKENDS = [
k for k, v in ASYNC_REQUEST_FUNCS.items()
if v in (async_request_openai_completions,
async_request_openai_chat_completions)
]

168
benchmarks/latency.py Normal file
View File

@@ -0,0 +1,168 @@
# SPDX-License-Identifier: Apache-2.0
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
"""Benchmark the latency of processing a single batch of requests."""
import argparse
import dataclasses
import json
import os
import time
from typing import Any, Optional
import numpy as np
from tqdm import tqdm
import vllm.envs as envs
from vllm import LLM, SamplingParams
from vllm.benchmarks.utils import (convert_to_pytorch_benchmark_format,
write_to_json)
from vllm.engine.arg_utils import EngineArgs
from vllm.inputs import PromptType
from vllm.sampling_params import BeamSearchParams
def save_to_pytorch_benchmark_format(args: argparse.Namespace,
results: dict[str, Any]) -> None:
pt_records = convert_to_pytorch_benchmark_format(
args=args,
metrics={"latency": results["latencies"]},
extra_info={k: results[k]
for k in ["avg_latency", "percentiles"]})
if pt_records:
pt_file = f"{os.path.splitext(args.output_json)[0]}.pytorch.json"
write_to_json(pt_file, pt_records)
def add_cli_args(parser: argparse.ArgumentParser):
parser.add_argument("--input-len", type=int, default=32)
parser.add_argument("--output-len", type=int, default=128)
parser.add_argument("--batch-size", type=int, default=8)
parser.add_argument(
"--n",
type=int,
default=1,
help="Number of generated sequences per prompt.",
)
parser.add_argument("--use-beam-search", action="store_true")
parser.add_argument(
"--num-iters-warmup",
type=int,
default=10,
help="Number of iterations to run for warmup.",
)
parser.add_argument("--num-iters",
type=int,
default=30,
help="Number of iterations to run.")
parser.add_argument(
"--profile",
action="store_true",
help="profile the generation process of a single batch",
)
parser.add_argument(
"--output-json",
type=str,
default=None,
help="Path to save the latency results in JSON format.",
)
parser.add_argument(
"--disable-detokenize",
action="store_true",
help=("Do not detokenize responses (i.e. do not include "
"detokenization time in the latency measurement)"),
)
parser = EngineArgs.add_cli_args(parser)
# V1 enables prefix caching by default which skews the latency
# numbers. We need to disable prefix caching by default.
parser.set_defaults(enable_prefix_caching=False)
def main(args: argparse.Namespace):
if args.profile and not envs.VLLM_TORCH_PROFILER_DIR:
raise OSError(
"The environment variable 'VLLM_TORCH_PROFILER_DIR' is not set. "
"Please set it to a valid path to use torch profiler.")
engine_args = EngineArgs.from_cli_args(args)
# 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,
temperature=1.0,
top_p=1.0,
ignore_eos=True,
max_tokens=args.output_len,
detokenize=not args.disable_detokenize,
)
dummy_prompt_token_ids = np.random.randint(10000,
size=(args.batch_size,
args.input_len))
dummy_prompts: list[PromptType] = [{
"prompt_token_ids": batch
} for batch in dummy_prompt_token_ids.tolist()]
def llm_generate():
if not args.use_beam_search:
llm.generate(dummy_prompts,
sampling_params=sampling_params,
use_tqdm=False)
else:
llm.beam_search(
dummy_prompts,
BeamSearchParams(
beam_width=args.n,
max_tokens=args.output_len,
ignore_eos=True,
),
)
def run_to_completion(profile_dir: Optional[str] = None):
if profile_dir:
llm.start_profile()
llm_generate()
llm.stop_profile()
else:
start_time = time.perf_counter()
llm_generate()
end_time = time.perf_counter()
latency = end_time - start_time
return latency
print("Warming up...")
for _ in tqdm(range(args.num_iters_warmup), desc="Warmup iterations"):
run_to_completion(profile_dir=None)
if args.profile:
profile_dir = envs.VLLM_TORCH_PROFILER_DIR
print(f"Profiling (results will be saved to '{profile_dir}')...")
run_to_completion(profile_dir=profile_dir)
return
# Benchmark.
latencies = []
for _ in tqdm(range(args.num_iters), desc="Profiling iterations"):
latencies.append(run_to_completion(profile_dir=None))
latencies = np.array(latencies)
percentages = [10, 25, 50, 75, 90, 99]
percentiles = np.percentile(latencies, percentages)
print(f"Avg latency: {np.mean(latencies)} seconds")
for percentage, percentile in zip(percentages, percentiles):
print(f"{percentage}% percentile latency: {percentile} seconds")
# Output JSON results if specified
if args.output_json:
results = {
"avg_latency": np.mean(latencies),
"latencies": latencies.tolist(),
"percentiles": dict(zip(percentages, percentiles.tolist())),
}
with open(args.output_json, "w") as f:
json.dump(results, f, indent=4)
save_to_pytorch_benchmark_format(args, results)

1135
benchmarks/serve.py Normal file

File diff suppressed because it is too large Load Diff

609
benchmarks/throughput.py Normal file
View File

@@ -0,0 +1,609 @@
# SPDX-License-Identifier: Apache-2.0
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
"""Benchmark offline inference throughput."""
import argparse
import dataclasses
import json
import os
import random
import time
import warnings
from typing import Any, Optional, Union
import torch
import uvloop
from tqdm import tqdm
from transformers import (AutoModelForCausalLM, AutoTokenizer,
PreTrainedTokenizerBase)
from vllm.benchmarks.datasets import (AIMODataset, BurstGPTDataset,
ConversationDataset,
InstructCoderDataset, RandomDataset,
SampleRequest, ShareGPTDataset,
SonnetDataset, VisionArenaDataset)
from vllm.benchmarks.utils import (convert_to_pytorch_benchmark_format,
write_to_json)
from vllm.engine.arg_utils import AsyncEngineArgs, EngineArgs
from vllm.entrypoints.openai.api_server import (
build_async_engine_client_from_engine_args)
from vllm.inputs import TextPrompt, TokensPrompt
from vllm.lora.request import LoRARequest
from vllm.outputs import RequestOutput
from vllm.sampling_params import BeamSearchParams
from vllm.utils import merge_async_iterators
def run_vllm(
requests: list[SampleRequest],
n: int,
engine_args: EngineArgs,
disable_detokenize: bool = False,
) -> tuple[float, Optional[list[RequestOutput]]]:
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[Union[TextPrompt, TokensPrompt]] = []
sampling_params: list[SamplingParams] = []
for request in requests:
prompts.append(
TokensPrompt(prompt_token_ids=request.prompt["prompt_token_ids"],
multi_modal_data=request.multi_modal_data)
if "prompt_token_ids" in request.prompt else \
TextPrompt(prompt=request.prompt,
multi_modal_data=request.multi_modal_data))
sampling_params.append(
SamplingParams(
n=n,
temperature=1.0,
top_p=1.0,
ignore_eos=True,
max_tokens=request.expected_output_len,
detokenize=not disable_detokenize,
))
lora_requests: Optional[list[LoRARequest]] = None
if engine_args.enable_lora:
lora_requests = [request.lora_request for request in requests]
use_beam_search = False
outputs = None
if not use_beam_search:
start = time.perf_counter()
outputs = llm.generate(prompts,
sampling_params,
lora_request=lora_requests,
use_tqdm=True)
end = time.perf_counter()
else:
assert lora_requests is None, "BeamSearch API does not support LoRA"
prompts = [request.prompt for request in requests]
# output_len should be the same for all requests.
output_len = requests[0][2]
for request in requests:
assert request.expected_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, outputs
def run_vllm_chat(
requests: list[SampleRequest],
n: int,
engine_args: EngineArgs,
disable_detokenize: bool = False) -> tuple[float, list[RequestOutput]]:
"""
Run vLLM chat benchmark. This function is recommended ONLY for benchmarking
multimodal models as it properly handles multimodal inputs and chat
formatting. For non-multimodal models, use run_vllm() instead.
"""
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.")
prompts = []
sampling_params: list[SamplingParams] = []
for request in requests:
prompts.append(request.prompt)
sampling_params.append(
SamplingParams(
n=n,
temperature=1.0,
top_p=1.0,
ignore_eos=True,
max_tokens=request.expected_output_len,
detokenize=not disable_detokenize,
))
start = time.perf_counter()
outputs = llm.chat(prompts, sampling_params, use_tqdm=True)
end = time.perf_counter()
return end - start, outputs
async def run_vllm_async(
requests: list[SampleRequest],
n: int,
engine_args: AsyncEngineArgs,
disable_frontend_multiprocessing: bool = False,
disable_detokenize: bool = False,
) -> float:
from vllm import SamplingParams
async with build_async_engine_client_from_engine_args(
engine_args, disable_frontend_multiprocessing) as llm:
model_config = await llm.get_model_config()
assert all(
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[Union[TextPrompt, TokensPrompt]] = []
sampling_params: list[SamplingParams] = []
lora_requests: list[Optional[LoRARequest]] = []
for request in requests:
prompts.append(
TokensPrompt(prompt_token_ids=request.prompt["prompt_token_ids"],
multi_modal_data=request.multi_modal_data)
if "prompt_token_ids" in request.prompt else \
TextPrompt(prompt=request.prompt,
multi_modal_data=request.multi_modal_data))
sampling_params.append(
SamplingParams(
n=n,
temperature=1.0,
top_p=1.0,
ignore_eos=True,
max_tokens=request.expected_output_len,
detokenize=not disable_detokenize,
))
lora_requests.append(request.lora_request)
generators = []
start = time.perf_counter()
for i, (prompt, sp,
lr) in enumerate(zip(prompts, sampling_params, lora_requests)):
generator = llm.generate(prompt,
sp,
lora_request=lr,
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[SampleRequest],
model: str,
tokenizer: PreTrainedTokenizerBase,
n: int,
max_batch_size: int,
trust_remote_code: bool,
disable_detokenize: bool = False,
) -> 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 = requests[i].prompt
prompt_len = requests[i].prompt_len
output_len = requests[i].expected_output_len
# 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 = requests[i + 1].prompt_len
next_output_len = requests[i + 1].expected_output_len
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,
)
if not disable_detokenize:
# 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 save_to_pytorch_benchmark_format(args: argparse.Namespace,
results: dict[str, Any]) -> None:
pt_records = convert_to_pytorch_benchmark_format(
args=args,
metrics={
"requests_per_second": [results["requests_per_second"]],
"tokens_per_second": [results["tokens_per_second"]],
},
extra_info={
k: results[k]
for k in ["elapsed_time", "num_requests", "total_num_tokens"]
})
if pt_records:
# Don't use json suffix here as we don't want CI to pick it up
pt_file = f"{os.path.splitext(args.output_json)[0]}.pytorch.json"
write_to_json(pt_file, pt_records)
def get_requests(args, tokenizer):
# Common parameters for all dataset types.
common_kwargs = {
"dataset_path": args.dataset_path,
"random_seed": args.seed,
}
sample_kwargs = {
"tokenizer": tokenizer,
"lora_path": args.lora_path,
"max_loras": args.max_loras,
"num_requests": args.num_prompts,
"input_len": args.input_len,
"output_len": args.output_len,
}
if args.dataset_path is None or args.dataset_name == "random":
sample_kwargs["range_ratio"] = args.random_range_ratio
sample_kwargs["prefix_len"] = args.prefix_len
dataset_cls = RandomDataset
elif args.dataset_name == "sharegpt":
dataset_cls = ShareGPTDataset
if args.backend == "vllm-chat":
sample_kwargs["enable_multimodal_chat"] = True
elif args.dataset_name == "sonnet":
assert tokenizer.chat_template or tokenizer.default_chat_template, (
"Tokenizer/model must have chat template for sonnet dataset.")
dataset_cls = SonnetDataset
sample_kwargs["prefix_len"] = args.prefix_len
sample_kwargs["return_prompt_formatted"] = True
elif args.dataset_name == "burstgpt":
dataset_cls = BurstGPTDataset
elif args.dataset_name == "hf":
if args.dataset_path in VisionArenaDataset.SUPPORTED_DATASET_PATHS:
dataset_cls = VisionArenaDataset
common_kwargs['dataset_subset'] = None
common_kwargs['dataset_split'] = "train"
sample_kwargs["enable_multimodal_chat"] = True
elif args.dataset_path in InstructCoderDataset.SUPPORTED_DATASET_PATHS:
dataset_cls = InstructCoderDataset
common_kwargs['dataset_split'] = "train"
elif args.dataset_path in ConversationDataset.SUPPORTED_DATASET_PATHS:
dataset_cls = ConversationDataset
common_kwargs['dataset_subset'] = args.hf_subset
common_kwargs['dataset_split'] = args.hf_split
sample_kwargs["enable_multimodal_chat"] = True
elif args.dataset_path in AIMODataset.SUPPORTED_DATASET_PATHS:
dataset_cls = AIMODataset
common_kwargs['dataset_subset'] = None
common_kwargs['dataset_split'] = "train"
else:
raise ValueError(f"Unknown dataset name: {args.dataset_name}")
# Remove None values
sample_kwargs = {k: v for k, v in sample_kwargs.items() if v is not None}
return dataset_cls(**common_kwargs).sample(**sample_kwargs)
def validate_args(args):
"""
Validate command-line arguments.
"""
# === Deprecation and Defaulting ===
if args.dataset is not None:
warnings.warn(
"The '--dataset' argument will be deprecated in the next release. "
"Please use '--dataset-name' and '--dataset-path' instead.",
stacklevel=2)
args.dataset_path = args.dataset
if not getattr(args, "tokenizer", None):
args.tokenizer = args.model
# === Backend Validation ===
valid_backends = {"vllm", "hf", "mii", "vllm-chat"}
if args.backend not in valid_backends:
raise ValueError(f"Unsupported backend: {args.backend}")
# === Dataset Configuration ===
if not args.dataset and not args.dataset_path:
print(
"When dataset path is not set, it will default to random dataset")
args.dataset_name = 'random'
if args.input_len is None:
raise ValueError("input_len must be provided for a random dataset")
# === Dataset Name Specific Checks ===
# --hf-subset and --hf-split: only used
# when dataset_name is 'hf'
if args.dataset_name != "hf" and (
getattr(args, "hf_subset", None) is not None
or getattr(args, "hf_split", None) is not None):
warnings.warn("--hf-subset and --hf-split will be ignored \
since --dataset-name is not 'hf'.",
stacklevel=2)
elif args.dataset_name == "hf":
if args.dataset_path in (
VisionArenaDataset.SUPPORTED_DATASET_PATHS.keys()
| ConversationDataset.SUPPORTED_DATASET_PATHS):
assert args.backend == "vllm-chat", f"{args.dataset_path} needs to use vllm-chat as the backend." #noqa: E501
elif args.dataset_path in (InstructCoderDataset.SUPPORTED_DATASET_PATHS
| AIMODataset.SUPPORTED_DATASET_PATHS):
assert args.backend == "vllm", f"{args.dataset_path} needs to use vllm as the backend." #noqa: E501
else:
raise ValueError(
f"{args.dataset_path} is not supported by hf dataset.")
# --random-range-ratio: only used when dataset_name is 'random'
if args.dataset_name != 'random' and args.random_range_ratio is not None:
warnings.warn("--random-range-ratio will be ignored since \
--dataset-name is not 'random'.",
stacklevel=2)
# --prefix-len: only used when dataset_name is 'random', 'sonnet', or not
# set.
if args.dataset_name not in {"random", "sonnet", None
} and args.prefix_len is not None:
warnings.warn("--prefix-len will be ignored since --dataset-name\
is not 'random', 'sonnet', or not set.",
stacklevel=2)
# === LoRA Settings ===
if getattr(args, "enable_lora", False) and args.backend != "vllm":
raise ValueError(
"LoRA benchmarking is only supported for vLLM backend")
if getattr(args, "enable_lora", False) and args.lora_path is None:
raise ValueError("LoRA path must be provided when enable_lora is True")
# === Backend-specific Validations ===
if args.backend == "hf" and args.hf_max_batch_size is None:
raise ValueError("HF max batch size is required for HF backend")
if args.backend != "hf" and args.hf_max_batch_size is not None:
raise ValueError("HF max batch size is only for HF backend.")
if args.backend in {"hf", "mii"} and getattr(args, "quantization",
None) is not None:
raise ValueError("Quantization is only for vLLM backend.")
if args.backend == "mii" and args.dtype != "auto":
raise ValueError("dtype must be auto for MII backend.")
if args.backend == "mii" and args.n != 1:
raise ValueError("n must be 1 for MII backend.")
if args.backend == "mii" and args.tokenizer != args.model:
raise ValueError(
"Tokenizer must be the same as the model for MII backend.")
def add_cli_args(parser: argparse.ArgumentParser):
parser.add_argument("--backend",
type=str,
choices=["vllm", "hf", "mii", "vllm-chat"],
default="vllm")
parser.add_argument(
"--dataset-name",
type=str,
choices=["sharegpt", "random", "sonnet", "burstgpt", "hf"],
help="Name of the dataset to benchmark on.",
default="sharegpt")
parser.add_argument(
"--dataset",
type=str,
default=None,
help="Path to the ShareGPT dataset, will be deprecated in\
the next release. The dataset is expected to "
"be a json in form of list[dict[..., conversations: "
"list[dict[..., value: <prompt_or_response>]]]]")
parser.add_argument("--dataset-path",
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.add_argument(
"--disable-detokenize",
action="store_true",
help=("Do not detokenize the response (i.e. do not include "
"detokenization time in the measurement)"))
# LoRA
parser.add_argument(
"--lora-path",
type=str,
default=None,
help="Path to the lora adapters to use. This can be an absolute path, "
"a relative path, or a Hugging Face model identifier.")
parser.add_argument(
"--prefix-len",
type=int,
default=0,
help="Number of fixed prefix tokens before the random "
"context in a request (default: 0).",
)
# random dataset
parser.add_argument(
"--random-range-ratio",
type=float,
default=0.0,
help="Range ratio for sampling input/output length, "
"used only for RandomDataset. Must be in the range [0, 1) to define "
"a symmetric sampling range "
"[length * (1 - range_ratio), length * (1 + range_ratio)].",
)
# hf dtaset
parser.add_argument("--hf-subset",
type=str,
default=None,
help="Subset of the HF dataset.")
parser.add_argument("--hf-split",
type=str,
default=None,
help="Split of the HF dataset.")
parser = AsyncEngineArgs.add_cli_args(parser)
def main(args: argparse.Namespace):
if args.tokenizer is None:
args.tokenizer = args.model
validate_args(args)
if args.seed is None:
args.seed = 0
random.seed(args.seed)
# Sample the requests.
tokenizer = AutoTokenizer.from_pretrained(
args.tokenizer, trust_remote_code=args.trust_remote_code)
requests = get_requests(args, tokenizer)
is_multi_modal = any(request.multi_modal_data is not None
for request in requests)
request_outputs: Optional[list[RequestOutput]] = None
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,
args.disable_detokenize,
))
else:
elapsed_time, request_outputs = run_vllm(
requests, args.n, EngineArgs.from_cli_args(args),
args.disable_detokenize)
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,
args.disable_detokenize)
elif args.backend == "vllm-chat":
elapsed_time, request_outputs = run_vllm_chat(
requests, args.n, EngineArgs.from_cli_args(args),
args.disable_detokenize)
else:
raise ValueError(f"Unknown backend: {args.backend}")
if request_outputs:
# Note: with the vllm and vllm-chat backends,
# we have request_outputs, which we use to count tokens.
total_prompt_tokens = 0
total_output_tokens = 0
for ro in request_outputs:
if not isinstance(ro, RequestOutput):
continue
total_prompt_tokens += len(
ro.prompt_token_ids) if ro.prompt_token_ids else 0
total_output_tokens += sum(
len(o.token_ids) for o in ro.outputs if o)
total_num_tokens = total_prompt_tokens + total_output_tokens
else:
total_num_tokens = sum(r.prompt_len + r.expected_output_len
for r in requests)
total_output_tokens = sum(r.expected_output_len for r in requests)
total_prompt_tokens = total_num_tokens - total_output_tokens
if is_multi_modal and args.backend != "vllm-chat":
print("\033[91mWARNING\033[0m: Multi-modal request with "
f"{args.backend} backend detected. The "
"following metrics are not accurate because image tokens are not"
" counted. See vllm-project/vllm/issues/9778 for details.")
# TODO(vllm-project/vllm/issues/9778): Count multi-modal token length.
# vllm-chat backend counts the image tokens now
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")
print(f"Total num prompt tokens: {total_prompt_tokens}")
print(f"Total num output tokens: {total_output_tokens}")
# 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)
save_to_pytorch_benchmark_format(args, results)

70
benchmarks/utils.py Normal file
View File

@@ -0,0 +1,70 @@
# SPDX-License-Identifier: Apache-2.0
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
import argparse
import json
import math
import os
from typing import Any
def convert_to_pytorch_benchmark_format(args: argparse.Namespace,
metrics: dict[str, list],
extra_info: dict[str, Any]) -> list:
"""
Save the benchmark results in the format used by PyTorch OSS benchmark with
on metric per record
https://github.com/pytorch/pytorch/wiki/How-to-integrate-with-PyTorch-OSS-benchmark-database
"""
records = []
if not os.environ.get("SAVE_TO_PYTORCH_BENCHMARK_FORMAT", False):
return records
for name, benchmark_values in metrics.items():
record = {
"benchmark": {
"name": "vLLM benchmark",
"extra_info": {
"args": vars(args),
},
},
"model": {
"name": args.model,
},
"metric": {
"name": name,
"benchmark_values": benchmark_values,
"extra_info": extra_info,
},
}
tp = record["benchmark"]["extra_info"]["args"].get(
"tensor_parallel_size")
# Save tensor_parallel_size parameter if it's part of the metadata
if not tp and "tensor_parallel_size" in extra_info:
record["benchmark"]["extra_info"]["args"][
"tensor_parallel_size"] = extra_info["tensor_parallel_size"]
records.append(record)
return records
class InfEncoder(json.JSONEncoder):
def clear_inf(self, o: Any):
if isinstance(o, dict):
return {k: self.clear_inf(v) for k, v in o.items()}
elif isinstance(o, list):
return [self.clear_inf(v) for v in o]
elif isinstance(o, float) and math.isinf(o):
return "inf"
return o
def iterencode(self, o: Any, *args, **kwargs) -> Any:
return super().iterencode(self.clear_inf(o), *args, **kwargs)
def write_to_json(filename: str, records: list) -> None:
with open(filename, "w") as f:
json.dump(records, f, cls=InfEncoder)