Skip to content

[Bugfix]: do not shutdown server if skip_special_use=False for MistralTokenizer #14094

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

Merged
merged 1 commit into from
Apr 10, 2025
Merged

[Bugfix]: do not shutdown server if skip_special_use=False for MistralTokenizer #14094

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
4 changes: 3 additions & 1 deletion vllm/entrypoints/openai/serving_chat.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -39,7 +39,8 @@
from vllm.sequence import Logprob
from vllm.transformers_utils.tokenizer import AnyTokenizer, MistralTokenizer
from vllm.transformers_utils.tokenizers import (maybe_serialize_tool_calls,
truncate_tool_call_ids)
truncate_tool_call_ids,
validate_request_params)

logger = init_logger(__name__)

Expand Down Expand Up @@ -159,6 +160,7 @@ async def create_chat_completion(
# for more info: see comment in `maybe_serialize_tool_calls`
maybe_serialize_tool_calls(request)
truncate_tool_call_ids(request)
validate_request_params(request)

if (request.tool_choice == "auto" and
not (self.enable_auto_tools and tool_parser is not None)
Expand Down
5 changes: 3 additions & 2 deletions vllm/transformers_utils/tokenizers/__init__.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,8 +1,9 @@
# SPDX-License-Identifier: Apache-2.0

from .mistral import (MistralTokenizer, maybe_serialize_tool_calls,
truncate_tool_call_ids)
truncate_tool_call_ids, validate_request_params)

__all__ = [
"MistralTokenizer", "maybe_serialize_tool_calls", "truncate_tool_call_ids"
"MistralTokenizer", "maybe_serialize_tool_calls", "truncate_tool_call_ids",
"validate_request_params"
]
7 changes: 7 additions & 0 deletions vllm/transformers_utils/tokenizers/mistral.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -98,6 +98,13 @@ def truncate_tool_call_ids(request: "ChatCompletionRequest"):
request.messages[i]["tool_call_id"] = tool_call_id


def validate_request_params(request: "ChatCompletionRequest"):
if (request.skip_special_tokens is not None
and not request.skip_special_tokens):
raise ValueError("skip_special_tokens=False is not supported "
"for Mistral tokenizers.")


def list_local_repo_files(repo_id: str, revision: Optional[str]) -> List[str]:
repo_cache = os.path.join(
huggingface_hub.constants.HF_HUB_CACHE,
Expand Down