v0.14.1
vllm-project/vllmv0.14.1Jan 24, 2026by khluu
AI Summary
A patch release focused on security vulnerabilities and memory leak fixes following v0.14.0.
Key Highlights
- Security fixes for HTTP header limits and eval usage
- Memory leak fixes
- Bugfixes for async-scheduling and FlashAttn MLA
New Features
- Bugfix for Ray with multiple nodes
- Fix false assertion with spec-decode and TP>2
- Fix async-scheduling + FlashAttn MLA compatibility
Full Release Notes
This is a patch release on top of `v0.14.0` to address a few security and memory leak fixes.