Skip to content

b10_lookahead speculation mode #1812

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

Jump to bottom
Draft
wants to merge 1 commit into
base: main
Choose a base branch
from
Draft

b10_lookahead speculation mode #1812

wants to merge 1 commit into from

Conversation

@mahmoudhas
Copy link
Contributor

@mahmoudhas mahmoudhas commented Jul 30, 2025

Adds speculation mode BASETEN_LOOKAHEAD as an alias to:

    speculator:
      speculative_decoding_mode: LOOKAHEAD_DECODING
      enable_b10_lookahead: true
      lookahead_windows_size: 1
      lookahead_ngram_size: 32
      lookahead_verification_set_size: 1

michaelfeil
michaelfeil reviewed Jul 31, 2025
View reviewed changes
truss/base/trt_llm_config.py
self._validate_spec_dec_mode()

def _resolve_baseten_lookahead(self):
if self.speculative_decoding_mode == TrussSpecDecMode.BASETEN_LOOKAHEAD:
Copy link
Contributor

@michaelfeil michaelfeil Jul 31, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I think this will not work and not persist. Its just how pydantic works.. :/

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@michaelfeil michaelfeil michaelfeil left review comments

At least 1 approving review is required to merge this pull request.

Assignees

No one assigned

Labels

None yet

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

3 participants

@mahmoudhas @michaelfeil