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

[Misc][Log] Add log for tokenizer length not equal to vocabulary size #3500

Merged
merged 1 commit into from
Mar 21, 2024
Merged

[Misc][Log] Add log for tokenizer length not equal to vocabulary size #3500

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
8 changes: 8 additions & 0 deletions vllm/engine/llm_engine.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -169,6 +169,14 @@ def _init_tokenizer(self, **tokenizer_init_kwargs):
self.tokenizer: BaseTokenizerGroup = get_tokenizer_group(
self.parallel_config.tokenizer_pool_config, **init_kwargs)

if len(self.get_tokenizer()) != self.model_config.get_vocab_size():
logger.warning(
f"The tokenizer's vocabulary size {len(self.get_tokenizer())}"
f" does not match the model's vocabulary size "
f"{self.model_config.get_vocab_size()}. This might "
f"cause an error in decoding. Please change config.json "
"to match the tokenizer's vocabulary size.")

def _verify_args(self) -> None:
self.model_config.verify_with_parallel_config(self.parallel_config)
self.cache_config.verify_with_parallel_config(self.parallel_config)
Expand Down
8 changes: 8 additions & 0 deletions vllm/entrypoints/openai/serving_engine.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -68,6 +68,14 @@ async def _post_init(self):
tokenizer_mode=engine_model_config.tokenizer_mode,
trust_remote_code=engine_model_config.trust_remote_code)

if len(self.tokenizer) != engine_model_config.get_vocab_size():
logger.warning(
f"The tokenizer's vocabulary size {len(self.tokenizer)}"
f" does not match the model's vocabulary size "
f"{engine_model_config.get_vocab_size()}. This might "
f"cause an error in decoding. Please change config.json "
"to match the tokenizer's vocabulary size.")

async def show_available_models(self) -> ModelList:
"""Show available models. Right now we only have one model."""
model_cards = [
Expand Down
Loading