# vLLM v0.6.5 — Release & Upgrade Intelligence
- **Product:** vLLM (https://vllm.ai)
- **Version:** v0.6.5
- **Released:** Dec 17, 2024
- **Impact Score:** 5/10
- **Breaking Changes:** Not verified
- **Canonical Analysis:** https://changelogs.us/vllm/updates/v0.6.5/

## Executive Summary (TL;DR)
vLLM v0.6.5. Source highlight: Significant progress on the V1 engine refactor and multimodal support: New model executable interfaces for text-only and multimodal models, multiprocessing, improved configuration handling, and profiling enhancements (#10374, #10570, #10699, #11074, #11076, #10382, #10665, #10564, #11125, #11185, #1

## New Features
- Added Aria (#10514), Cross Encoder (#10400), GLM-4 (#10561), OLMo (#10503), Telechat2 (#10311), Cohere R7B (#11203), GritLM embeddings (#10816)
- Add default value to avoid Falcon crash (#5363)
- [Docs] Add Nebius as sponsors
- [Frontend] Add --version flag to CLI
- [doc] add doc for the plugin system
- [V1] Add code owners for V1

## Improvements
- Significant progress on the V1 engine refactor and multimodal support: New model executable interfaces for text-only and multimodal models, multiprocessing, improved configuration handling, and profiling enhancements (#10374, #10570, #10699, #11074, #11076, #10382, #10665, #10564, #11125, #11185, #11242).
- Expanded model support, including Aria, Cross Encoders, GLM-4, OLMo November 2024, Telechat2, LoRA improvements and multimodal Granite models (#10514, #10400, #10561, #10503, #10311, #10291, #9057, #10418, #5064).
- Improved hardware enablement for AMD ROCm, ARM AARCH64, TPU prefix caching, XPU AWQ/GPTQ, and various CPU/Gaudi/HPU/NVIDIA enhancements (#10254, #9228, #10307, #10107, #10667, #10565, #10239, #11016, #9735, #10355, #10700).
- Improved quantization (BNB, bitsandbytes) for multiple models (#10795, #10842, #10682, #10549)
- AMD ROCm GGUF quantization (#10254), ARM AARCH64 enablement (#9228), TPU prefix caching (#10307), XPU AWQ/GPTQ (#10107), CPU/Gaudi/HPU enhancements (#10355, #10667, #10565, #10239, #11016, #9735, #10541, #10394, #10700).
- Prefix-cache aware scheduling (#10128), sliding window support (#10462), disaggregated prefill enhancements (#10502, #10884), evictor optimization (#7209).

## Bug Fixes
- Major improvements in `torch.compile` integration: Support for all attention backends, encoder-based models, dynamic FP8 fusion, shape specialization fixes, and performance optimizations (#10558, #10613, #10121, #10383, #10399, #10406, #10437, #10460, #10552, #10622, #10722, #10620, #10906, #11108, #11059, #11005, #10838, #11081, #11110).
- Updated defaults for chunked prefill (#10544)
- Add GH200 support (#11212, #11244)
- [Misc] Fix import error in tensorizer tests and cleanup some code
- [Bugfix] Fix fully sharded LoRA bug
- [Misc] Fix some help info of arg_utils to improve readability

## Upgrade Command
```bash
python -m pip install 'vllm==0.6.5'
```