Skip to content

GitLab

Commit 3904b5c4 authored by jerrrrry's avatar jerrrrry
Browse files

Delete benchmark_throughput_0.6.2.py

parent ef115ee8
Show whitespace changes
Inline Side-by-side
Showing with 0 additions and 731 deletions
benchmark_throughput_0.6.2.py deleted 100644 → 0
View file @ ef115ee8
"""Benchmark offline inference throughput."""
import argparse
import json
import random
import time
from typing import List, Optional, Tuple
import numpy as np
import torch
import uvloop
from tqdm import tqdm
from transformers import (AutoModelForCausalLM, AutoTokenizer,
PreTrainedTokenizerBase)
from vllm.inputs import PromptInputs
from vllm.engine.arg_utils import DEVICE_OPTIONS, 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.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(
warmup_requests: List[Tuple[str, int, int]],
requests_json: List[Tuple[str, int, int]],
model: str,
tokenizer: str,
quantization: Optional[str],
tensor_parallel_size: int,
seed: int,
n: int,
use_beam_search: bool,
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,
use_v2_block_manager: bool = False,
download_dir: Optional[str] = None,
load_format: str = EngineArgs.load_format,
disable_async_output_proc: bool = False,
use_new_beam_search_impl: bool = False,
) -> 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,
use_v2_block_manager=use_v2_block_manager,
disable_async_output_proc=disable_async_output_proc,
)
# warmup
warmup_prompts = []
warmup_sampling_params = []
for prompt, _, output_len in warmup_requests:
warmup_prompts.append(prompt)
warmup_sampling_params.append(
SamplingParams(
n=n,
temperature=0.0 if use_beam_search else 1.0,
top_p=1.0,
use_beam_search=use_beam_search,
ignore_eos=True,
max_tokens=output_len,
))
print("Warming up...")
for _ in tqdm(range(args.num_iters_warmup), desc="Warmup iterations"):
llm.generate(warmup_prompts, warmup_sampling_params, use_tqdm=True)
info_json={}
for ELEprompt in args.num_prompts:
for ELEinput,ELEoutput in zip(args.input_len,args.output_len):
info={}
requests=requests_json["{}_{}_{}".format(ELEprompt,ELEinput,ELEoutput)]
# 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=0.0 if use_beam_search else 1.0,
top_p=1.0,
use_beam_search=use_beam_search,
ignore_eos=True,
max_tokens=output_len,
))
if not use_new_beam_search_impl:
start = time.perf_counter()
real_output = llm.generate(prompts, sampling_params, use_tqdm=True)
end = time.perf_counter()
else:
assert use_beam_search
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,
beam_width=n,
max_tokens=output_len,
ignore_eos=True)
end = time.perf_counter()
total_ttfts = []
total_tpops = []
total_output_token_throughput = []
total_inout_token_throughput = []
for output in real_output:
ttft_ = output.metrics.first_token_time - output.metrics.arrival_time
tpop_ = (output.metrics.finished_time - output.metrics.arrival_time - ttft_) / (ELEoutput-1)
output_token_throughput = (ELEoutput) / (output.metrics.finished_time - output.metrics.arrival_time)
inout_token_throughput = (ELEoutput + ELEinput) / (output.metrics.finished_time - output.metrics.arrival_time)
total_ttfts.append(ttft_)
total_tpops.append(tpop_)
total_output_token_throughput.append(output_token_throughput)
total_inout_token_throughput.append(inout_token_throughput)
# total_num_tokens = sum(request.prompt_len + request.expected_output_len
# for request in requests)
# total_output_tokens = sum(request.expected_output_len
# for request in requests)
total_num_tokens = sum(prompt_len + output_len
for _, prompt_len, output_len in requests)
total_output_tokens = sum(output_len
for _, prompt_len, output_len in requests)
info["elapsed_time"] = np.around(end - start,2)
info["Throughput"] = np.around(len(requests) / info['elapsed_time'],2)
info["total_tokens"] = np.around(total_num_tokens / info['elapsed_time'],2)
info["output_tokens"] = np.around(total_output_tokens / info['elapsed_time'],2)
info["ttft_mean"] = np.around(np.mean(total_ttfts),5)
info["ttft_median"] = np.around(np.median(total_ttfts or 0),5)
info["ttft_p99"] = np.around(np.percentile(total_ttfts or 0, 99),5)
info["tpop_mean"] = np.around(np.mean(total_tpops),4)
info["tpop_median"] = np.around(np.median(total_tpops or 0),5)
info["tpop_p99"] = np.around(np.percentile(total_tpops or 0, 99),5)
info["output_token_throughput_mean"] = np.around(np.mean(total_output_token_throughput),2)
info["output_token_throughput_median"] = np.around(np.median(total_output_token_throughput or 0),2)
info["output_token_throughput_p99"] = np.around(np.percentile(total_output_token_throughput or 0, 99),2)
info["inout_token_throughput_mean"] = np.around(np.mean(total_inout_token_throughput),2)
info["inout_token_throughput_median"] = np.around(np.median(total_inout_token_throughput or 0),2)
info["inout_token_throughput_p99"] = np.around(np.percentile(total_inout_token_throughput or 0, 99),2)
info_json["{}_{}_{}".format(ELEprompt,ELEinput,ELEoutput)] = info
print("promt:{},input:{},output:{}".format(ELEprompt,ELEinput,ELEoutput))
print(f"Latency: {info['elapsed_time']:.2f} s")
print(f"Throughput: {len(requests) / info['elapsed_time']:.2f} requests/s, "
f"{total_num_tokens / info['elapsed_time']:.2f} total tokens/s, "
f"{total_output_tokens / info['elapsed_time']:.2f} output tokens/s")
print("==============================================")
print(f"total_out_tokens: {total_output_tokens: .2f} tokens")
print(f"elapsed_time: {info['elapsed_time']: .2f} s") # 总耗时
print(f"TTFT_mean: {info['ttft_mean']: .5f} s") # 首字延时
print(f"ttft_p99: {info['ttft_p99']: .5f} s")
print(f"ttft_median: {info['ttft_median']: .5f} s")
print(f"TPOP_mean: {info['tpop_mean']: .5f} s") # 单字decode时间
print(f"tpop_median: {info['tpop_median']: .5f} s")
print(f"tpop_p99: {info['tpop_p99']: .5f} s")
print(f"output_token_throughput_mean: {info['output_token_throughput_mean']:.2f} tokens/s") # 单路生成吞吐
print(f"output_token_throughput_median: {info['output_token_throughput_median']:.2f} tokens/s")
print(f"output_token_throughput_p99: {info['output_token_throughput_p99']:.2f} tokens/s")
print(f"inout_token_throughput_mean: {info['inout_token_throughput_mean']:.2f} tokens/s") # 单路总吞吐
print(f"tinout_token_throughput_median: {info['inout_token_throughput_median']:.2f} tokens/s")
print(f"inout_token_throughput_p99: {info['inout_token_throughput_p99']:.2f} tokens/s")
print("==============================================")
print("\n")
return info_json
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,
use_beam_search: bool,
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,
use_v2_block_manager: bool = False,
download_dir: Optional[str] = None,
load_format: str = EngineArgs.load_format,
disable_async_output_proc: bool = False,
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,
use_v2_block_manager=use_v2_block_manager,
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:
# 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=0.0 if use_beam_search else 1.0,
top_p=1.0,
use_beam_search=use_beam_search,
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,
use_beam_search: bool,
max_batch_size: int,
trust_remote_code: bool,
) -> float:
assert not use_beam_search
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=not use_beam_search,
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)
warmup_prompt = "hi" * 10
warmup_requests = [(warmup_prompt, 10, 10)
for _ in range(1)]
if args.dataset is None:
requests_json={}
for ELEprompt in args.num_prompts:
for ELEinput,ELEoutput in zip(args.input_len,args.output_len):
# Synthesize a prompt with the given input length.
prompt = "hi" * (ELEinput - 1)
requests = [(prompt, ELEinput, ELEoutput)
for _ in range(ELEprompt)]
print("type(requests):",type(requests))
requests_json["{}_{}_{}".format(ELEprompt,ELEinput,ELEoutput)]=requests
else:
requests = sample_requests(args.dataset, args.num_prompts, tokenizer,
args.output_len)
if args.backend == "vllm":
if args.async_engine:
run_args = [
requests, args.model, args.tokenizer, args.quantization,
args.tensor_parallel_size, args.seed, args.n, args.use_beam_search,
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.use_v2_block_manager, args.download_dir, args.load_format,
args.disable_async_output_proc
]
else:
run_args = [
warmup_requests, requests_json, args.model, args.tokenizer, args.quantization,
args.tensor_parallel_size, args.seed, args.n, args.use_beam_search,
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.use_v2_block_manager, 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))
else:
info_json = run_vllm(*run_args, args.use_new_beam_search_impl)
elif args.backend == "hf":
assert args.tensor_parallel_size == 1
elapsed_time = run_hf(requests, args.model, tokenizer, args.n,
args.use_beam_search, 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)
# if args.dataset is None:
# total_out_tokens = args.output_len * args.num_prompts
# else:
# total_out_tokens = sum(output_len for _, _, output_len in requests)
# print(f"Latency: {elapsed_time:.2f} s")
# print(f"All Throughput: {len(requests) / elapsed_time:.2f} requests/s, "
# f"{total_num_tokens / elapsed_time:.2f} tokens/s")
# print(f"Generate Throughput: {total_out_tokens / elapsed_time:.2f} tokens/s")
with open(args.output_json,"w") as f:
title="bs_in_out"
data_keys=info_json[list(info_json.keys())[0]].keys()
keys_string = ','.join(data_keys)
title=title+","+keys_string
f.write(title)
f.write("\n")
for key, value in info_json.items():
values_as_strings = [str(value) for value in info_json[key].values()]
values_string = ','.join(values_as_strings)
key=key+","+values_string
f.writelines(key)
f.write("\n")
# 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,
nargs="*",
default=None,
help="Input prompt length for each request")
parser.add_argument("--output-len",
type=int,
nargs="*",
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,
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=1,
help='Number of iterations to run for warmup.')
parser.add_argument("--use-new-beam-search-impl", action="store_true")
parser.add_argument("--num-prompts",
nargs="*",
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 (hcu) 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 (hcu), 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("--use-v2-block-manager",
action='store_true',
help="Enable block manager v2.")
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,
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.")
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.use_beam_search:
raise ValueError("Beam search is not supported 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)
\ No newline at end of file
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment