refactor: replace gevent threadpool with ProcessPoolExecutor in GPT2Tokenizer (#12316)

Signed-off-by: -LAN- <laipz8200@outlook.com>
This commit is contained in:
-LAN- 2025-01-03 09:13:18 +08:00 committed by GitHub
parent 52b2559a14
commit 6f5a8a33d9
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194

View File

@ -1,13 +1,13 @@
from concurrent.futures import ProcessPoolExecutor
from os.path import abspath, dirname, join
from threading import Lock
from typing import Any, cast
import gevent.threadpool # type: ignore
from transformers import GPT2Tokenizer as TransformerGPT2Tokenizer # type: ignore
_tokenizer: Any = None
_lock = Lock()
_pool = gevent.threadpool.ThreadPool(1)
_executor = ProcessPoolExecutor(max_workers=1)
class GPT2Tokenizer:
@ -22,8 +22,8 @@ class GPT2Tokenizer:
@staticmethod
def get_num_tokens(text: str) -> int:
future = _pool.spawn(GPT2Tokenizer._get_num_tokens_by_gpt2, text)
result = future.get(block=True)
future = _executor.submit(GPT2Tokenizer._get_num_tokens_by_gpt2, text)
result = future.result()
return cast(int, result)
@staticmethod