# vLLM v0.6.1.post1 — Release & Upgrade Intelligence
- **Product:** vLLM (https://vllm.ai)
- **Version:** v0.6.1.post1
- **Released:** Sep 13, 2024
- **Impact Score:** 5/10
- **Breaking Changes:** Not verified
- **Canonical Analysis:** https://changelogs.us/vllm/updates/v0.6.1.post1/

## Executive Summary (TL;DR)
vLLM v0.6.1.post1. Source highlight: This release features important bug fixes and enhancements for

## New Features
- add engine option to return only deltas or final output (#7381)
- add bitsandbytes support for Gemma2 (#8338)
- [Gemma2] add bitsandbytes support for Gemma2
- [multi-step] add flashinfer backend
- [Core] Add engine option to return only deltas or final output

## Bug Fixes
- Fix the AMD weight loading tests
- [Bugfix]: Fix the logic for deciding if tool parsing is used
- [Bugfix] Fix InternVL2 inference with various num_patches
- [BugFix] lazy init _copy_stream to avoid torch init wrong gpu instance
- [BugFix] Fix Duplicate Assignment of Class Variable in Hermes2ProToolParser
- [Bugfix] Offline mode fix