v0.8.5.post1

vllm-project/vllmv0.8.5.post1May 2, 2025by github-actions[bot]

AI Summary

A post-release patch containing bugfixes for memory leaks and model accuracy issues.

Key Highlights

Bugfix: Fix Memory Leak in `_cached_reqs_data`.
Bugfix: Fix sliding window attention in V1 giving incorrect results.

Full Release Notes

This post release contains two bug fix for memory leak and model accuracy

* Fix Memory Leak in `_cached_reqs_data` (#17567)
* Fix sliding window attention in V1 giving incorrect results (#17574)

**Full Changelog**: https://github.com/vllm-project/vllm/compare/v0.8.5...v0.8.5.post1