vLLM v0.28.0

v0.28.0
Highlights
This release features 584 commits from 270 contributors (76 new)!

Kimi-K3 performance push: a major optimization effort for Kimi-K3 across the stack — Decode Context Parallel (D...
93 points by mrrrcs 53 days ago github.com 31 comments

Summary

The latest release of vLLM includes significant optimizations for Kimi-K3, driven by contributions from a large community of developers. With 584 commits and a focus on performance enhancements, this update promises to improve efficiency and user experience.

Comments (31 of ) ⌛

Loading more comments... ⌛
Scroll down to load more comments
No comments available.
Type to search HN and engineering blog articles
Press Escape to close  |  ↑↓ to navigate  |  Enter to open