Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

feat: implement asynchronous token counting in GPT2Tokenizer #12239

Merged
merged 2 commits into from
Dec 31, 2024
Merged

feat: implement asynchronous token counting in GPT2Tokenizer #12239

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
744c96d
feat: implement asynchronous token counting in GPT2Tokenizer
laipz8200 Dec 30, 2024
e3763ca
feat: replace ProcessPoolExecutor with gevent threadpool for token co…
laipz8200 Dec 31, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 6 additions & 2 deletions api/core/model_runtime/model_providers/__base/tokenizers/gpt2_tokenzier.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,11 +1,13 @@
from os.path import abspath, dirname, join
from threading import Lock
from typing import Any
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)


class GPT2Tokenizer:
Expand All @@ -20,7 +22,9 @@ def _get_num_tokens_by_gpt2(text: str) -> int:

@staticmethod
def get_num_tokens(text: str) -> int:
return GPT2Tokenizer._get_num_tokens_by_gpt2(text)
future = _pool.spawn(GPT2Tokenizer._get_num_tokens_by_gpt2, text)
result = future.get(block=True)
return cast(int, result)

@staticmethod
def get_encoder() -> Any:
Expand Down
Loading