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.

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

[vllm] Validate speculative model config #2415

Merged
merged 1 commit into from
Oct 2, 2024

Conversation

xyang16
Copy link
Contributor

@xyang16 xyang16 commented Oct 2, 2024

Description

Brief description of what this PR is about

  • If this change is a backward incompatible change, why must this change be made?
  • Interesting edge cases to note here

@xyang16 xyang16 requested review from zachgk and a team as code owners October 2, 2024 22:53
@xyang16 xyang16 merged commit 45454f7 into deepjavalibrary:master Oct 2, 2024
9 checks passed
def validate_speculative_model(self):
if self.speculative_model is not None and not self.use_v2_block_manager:
raise ValueError(
"Speculative decoding requires usage of the V2 block manager. Enable it with option.use_v2_block_manager=true."
Copy link
Contributor

@davidthomas426 davidthomas426 Oct 3, 2024

Choose a reason for hiding this comment

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

That's actually not true. [EDIT: I was wrong! Check next comment for details]

Copy link
Contributor

@davidthomas426 davidthomas426 Oct 3, 2024

Choose a reason for hiding this comment

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

Ok, just double-checked. It actually is true. I was confused by the inconsistency between these two pieces of code in vllm v0.6.2:

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants