Skip to content

Navigation Menu

Explore
By company size
By use case
By industry
View all solutions
Topics
- AI
- DevOps
- Security
- Software Development
- View all
Explore
- GitHub Sponsors
  Fund open source developers
- The ReadME Project
  GitHub community articles
Repositories
- Enterprise platform
  AI-powered developer platform
Available add-ons
Pricing

Search code, repositories, users, issues, pull requests...

Search

Clear

Search syntax tips

Provide feedback

We read every piece of feedback, and take your input very seriously.

Include my email address so I can be contacted

Saved searches

Use saved searches to filter your results more quickly

Name

Query

To see all available qualifiers, see our documentation.

You signed in with another tab or window. Reload to refresh your session. You signed out in another tab or window. Reload to refresh your session. You switched accounts on another tab or window. Reload to refresh your session.

Dismiss alert

vllm-project / vllm Public

Notifications You must be signed in to change notification settings
Fork 6.2k
Star 41.2k

Code
Issues 1.4k
Pull requests 491
Discussions
Actions
Projects 5
Security
Insights

Additional navigation options

Code
Issues
Pull requests
Discussions
Actions
Projects
Security
Insights

[Bugfix] Fix for inconsistent behaviour related to sampling and repetition penalties #5639

Merged

simon-mo merged 4 commits intovllm-project:mainvllm-project/vllm:mainfrom tdoublep:sampling-penalties-fixtdoublep/vllm:sampling-penalties-fixCopy head branch name to clipboard

Jun 18, 2024

Conversation Commits4 (4)Checks Files changed

Commits

Commits on Jun 18, 2024

Calculate do_penalties upfront
tdoublep
committed
Format
tdoublep
committed
Compute prompt_tokens and output_tokens in second pass so that do_penalties is consistently computed across sequence groups.
tdoublep
committed
Minor cleanup
tdoublep
committed

Footer

© 2025 GitHub, Inc.

Footer navigation

Terms
Privacy
Security
Status
Docs
Contact

You can’t perform that action at this time.