Skip to content

[Bugfix] Better error message for MLPSpeculator when num_speculative_tokens is set too high #5894

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 2 commits into from
Jun 28, 2024
Merged

[Bugfix] Better error message for MLPSpeculator when num_speculative_tokens is set too high #5894

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
30a3f8c
MLPSpeculator: Better error message when num_speculative_tokens is se…
tdoublep Jun 27, 2024
e8f30f7
Merge branch 'main' into mlp-error-msg
tdoublep Jun 28, 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
6 changes: 3 additions & 3 deletions vllm/config.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -951,9 +951,9 @@ def maybe_create_spec_config(
# Verify provided value doesn't exceed the maximum
# supported by the draft model.
raise ValueError(
"Expected both speculative_model and "
"num_speculative_tokens to be provided, but found "
f"{speculative_model=} and {num_speculative_tokens=}.")
"This speculative model supports a maximum of "
f"num_speculative_tokens={n_predict}, but "
f"{num_speculative_tokens=} was provided.")

draft_model_config.max_model_len = (
SpeculativeConfig._maybe_override_draft_max_model_len(
Expand Down