94 lines
2.7 KiB
Python
94 lines
2.7 KiB
Python
import json
|
|
import time
|
|
from argparse import ArgumentParser
|
|
from concurrent.futures import ThreadPoolExecutor
|
|
from functools import partial
|
|
|
|
from data_gen import gen_arguments
|
|
from tqdm import tqdm
|
|
from vllm.transformers_utils.tokenizer import get_tokenizer
|
|
|
|
from sglang.test.test_utils import add_common_other_args_and_parse, get_call_generate
|
|
from sglang.utils import dump_state_text
|
|
|
|
|
|
def multi_turns(generate, qas):
|
|
s = ""
|
|
for qa in qas:
|
|
s += qa["prompt"]
|
|
s += generate(s, max_tokens=qa["new_tokens"])
|
|
|
|
return s
|
|
|
|
|
|
def main(args):
|
|
print(args)
|
|
|
|
tokenizer = get_tokenizer(args.tokenizer, trust_remote_code=args.trust_remote_code)
|
|
|
|
multi_qas = gen_arguments(args, tokenizer)
|
|
|
|
states = [None] * args.num_qa
|
|
|
|
call_generate = partial(get_call_generate(args), temperature=0)
|
|
|
|
def get_one_answer(i):
|
|
states[i] = multi_turns(generate=call_generate, **multi_qas[i])
|
|
|
|
tic = time.time()
|
|
if args.parallel == 1:
|
|
for i in tqdm(range(len(multi_qas))):
|
|
get_one_answer(i)
|
|
else:
|
|
with ThreadPoolExecutor(args.parallel) as executor:
|
|
rets = list(
|
|
tqdm(
|
|
executor.map(get_one_answer, list(range(len(multi_qas)))),
|
|
total=len(multi_qas),
|
|
)
|
|
)
|
|
for _ in rets:
|
|
pass
|
|
|
|
latency = time.time() - tic
|
|
|
|
# Compute accuracy
|
|
print(f"Latency: {latency:.3f}")
|
|
|
|
dump_state_text(f"tmp_output_{args.backend}.txt", states)
|
|
|
|
with open(args.result_file, "a") as fout:
|
|
value = {
|
|
"task": "multi_turn_chat",
|
|
"backend": args.backend,
|
|
"num_gpus": 1,
|
|
"latency": round(latency, 3),
|
|
"num_requests": args.num_qa,
|
|
"num_turns": args.turns,
|
|
"other": {
|
|
"parallel": args.parallel,
|
|
"output_mode": "long" if args.long else "short",
|
|
},
|
|
}
|
|
fout.write(json.dumps(value) + "\n")
|
|
|
|
|
|
if __name__ == "__main__":
|
|
parser = ArgumentParser()
|
|
parser.add_argument("--turns", type=int, default=4)
|
|
parser.add_argument("--num-qa", type=int, default=20)
|
|
parser.add_argument("--min-len-q", type=int, default=256)
|
|
parser.add_argument("--max-len-q", type=int, default=512)
|
|
parser.add_argument("--min-len-a", type=int, default=4)
|
|
parser.add_argument("--max-len-a", type=int, default=8)
|
|
parser.add_argument("--tokenizer", type=str, required=True)
|
|
parser.add_argument("--trust-remote-code", action="store_true")
|
|
parser.add_argument("--long", action="store_true")
|
|
args = add_common_other_args_and_parse(parser)
|
|
|
|
if args.long:
|
|
args.min_len_a = 256
|
|
args.max_len_a = 512
|
|
args.num_qa = 20
|
|
main(args)
|