# vLLM v0.5.0.post1 — Release & Upgrade Intelligence
- **Product:** vLLM (https://vllm.ai)
- **Version:** v0.5.0.post1
- **Released:** Jun 14, 2024
- **Impact Score:** 5/10
- **Breaking Changes:** Not verified
- **Canonical Analysis:** https://changelogs.us/vllm/updates/v0.5.0.post1/

## Executive Summary (TL;DR)
vLLM v0.5.0.post1. Source highlight: Add initial TPU integration (#5292)

## New Features
- Add initial TPU integration (#5292)
- [CI/Build] Add `is_quant_method_supported` to control quantization test configurations
- Revert "[CI/Build] Add `is_quant_method_supported` to control quantization test configurations"
- [ci] Add AMD, Neuron, Intel tests for AWS CI and turn off default soft fail for GPU tests
- [misc] add hint for AttributeError
- [Frontend] Add "input speed" to tqdm postfix alongside output speed

## Bug Fixes
- Fix crashes when using FlashAttention backend (#5478)
- Fix issues when using num_devices < num_available_devices (#5473)
- [Bugfix] Add device assertion to TorchSDPA
- [Bugfix] TYPE_CHECKING for MultiModalData
- [Doc] Update debug docs
- [Bugfix] Fix typo in scheduler.py (requeset -> request)