# vLLM v0.8.0 — Release & Upgrade Intelligence
- **Product:** vLLM (https://vllm.ai)
- **Version:** v0.8.0
- **Released:** Mar 18, 2025
- **Impact Score:** 7/10
- **Breaking Changes:** Source flagged
- **Canonical Analysis:** https://changelogs.us/vllm/updates/v0.8.0/

## Executive Summary (TL;DR)
vLLM v0.8.0. Source highlight: We have now enabled V1 engine by default (#13726) for supported use cases. Please refer to V1 user guide for more detail. We expect better performance for supported scenarios. If you'd like to disable V1 mode, please specify the environment variable `VLLM_USE_V1=0`, and send us a GitHub issue sharin

## Breaking Changes & Deprecations
- Breaking Changes * The default value of `seed` is now `None` to align with PyTorch and Hugging Face. Please explicitly set seed for reproduciblity. (#14274) * The `kv_cache` and `attn_metadata` arguments for model's forward method has been removed; as the attention backend has access to these value via `forward_context`. (#13887)
- [V1] Prevent xgrammar from breaking TPU support by @russellb in https://github.com/vllm-project/vllm/pull/14575

## New Features
- Add enable_expert_parallel arg (#14305)
- Add streamK for block-quantized CUTLASS kernels (#12978)
- Add benchmark for DeepGEMM and vLLM Block FP8 Dense GEMM (#13917)
- Add more tuned configs for H20 and others (#14877)
- Add cutlass support for blackwell fp8 gemm (#13798)
- Add ModelOpt FP4 Checkpoint Support (#12520)

## Improvements
- Metrics enhancements (#13299, #13504, #14695, #14082)
- Enhance Pipeline Parallelism (#14585, #14643)
- FlashMLA integration (#13747, #13867, #14451)
- MLA support for V1 (#13789, #14253, #14384, #14540, #14921)
- MLA with chunked prefill (#12639)
- Holistic memory and performance optimization (#14769, #14770,#14842)

## Bug Fixes
- Stability fixes (#14380, #14379, #13298)
- Upgrade aiohttp to incldue CVE fix (#14840)
- Upgrade jinja2 to get 3 moderate CVE fixes (#14839)
- Illegal memory access for MoE On H20 (#13693)
- Fix FP16 overflow for DeepSeek V2 (#13232)
- Illegal Memory Access in the blockwise cutlass fp8 GEMMs (#14396)

## Upgrade Command
```bash
python -m pip install 'vllm==0.8.0'
```