# vLLM v0.6.3.post1 — Release & Upgrade Intelligence
- **Product:** vLLM (https://vllm.ai)
- **Version:** v0.6.3.post1
- **Released:** Oct 17, 2024
- **Impact Score:** 5/10
- **Breaking Changes:** Not verified
- **Canonical Analysis:** https://changelogs.us/vllm/updates/v0.6.3.post1/

## Executive Summary (TL;DR)
vLLM v0.6.3.post1. Source highlight: Support Ministral 3B and Ministral 8B via interleaved attention (#9414)

## New Features
- Add notes on the use of Slack
- [Kernel] Add Exllama as a backend for compressed-tensors
- [CI/Build] remove .github from .dockerignore, add dirty repo check

## Improvements
- Remove block manager v1 and make block manager v2 default (#8704)
- Spec Decode Optimize ngram lookup performance (#9333)
- [Kernel][Model] Improve continuous batching for Jamba and Mamba
- [Performance][Spec Decode] Optimize ngram lookup performance

## Bug Fixes
- Fix chat API continuous usage stats (#9357)
- Fix vLLM UsageInfo and logprobs None AssertionError with empty token_ids (#9034)
- Fix Molmo text-only input bug (#9397)
- Fix CUDA 11.8 Build (#9386)
- Fix `_version.py` not found issue (#9375)
- [TPU] Fix TPU SMEM OOM by Pallas paged attention kernel