# vLLM v0.10.0 — Release & Upgrade Intelligence
- **Product:** vLLM (https://vllm.ai)
- **Version:** v0.10.0
- **Released:** Jul 24, 2025
- **Impact Score:** 5/10
- **Breaking Changes:** Not verified
- **Canonical Analysis:** https://changelogs.us/vllm/updates/v0.10.0/

## Executive Summary (TL;DR)
vLLM v0.10.0. Source highlight: v0.10.0 release includes 308 commits, 168 contributors (62 new!).

## New Features
- Add H20-3e fused MoE kernel tuning configs for Qwen3-235B-A22B-FP8
- Add fused MOE config for Qwen3 30B A3B on B200
- [ROCm] Add rules to automatically label ROCm related PRs
- [Misc] Reduce warning message introduced in env_override
- Add cache to cuda get_device_capability
- [Docs] Remove WIP features in V1 guide

## Improvements
- Enhanced compatibility: BERT/RoBERTa with AutoWeightsLoader (#20534), HF format support for MiniMax (#20211), Gemini configuration (#20971), GLM-4 updates (#20736).
- VLM improvements: VLM support with transformers backend (#20543), PrithviMAE on V1 engine (#20577).
- V1 engine improvements: backend-agnostic local attention (#21093), MLA FlashInfer ragged prefill (#20034), hybrid KV cache with local chunked attention (#19351).
- Enhanced caching: multi-modal caching for transformers backend (#21358), reproducible prefix cache hashing using SHA-256 + CBOR (#20511).
- NVIDIA Blackwell/SM100 optimizations: CUTLASS block scaled group GEMM for smaller batches (#20640), FP8 groupGEMM support (#20447), DeepGEMM integration (#20087), FlashInfer MoE blockscale FP8 backend (#20645), CUDNN prefill API for MLA (#20411), Triton Fused MoE kernel config for FP8 E=16 on B200 (#20516).
- Performance improvements: 48% request duration reduction via microbatch tokenization for concurrent requests (#19334), fused MLA QKV + strided layernorm (#21116), Triton causal-conv1d for Mamba models (#18218).

## Bug Fixes
- [BugFix] Allow use_cudagraph to work with dynamic VLLM_USE_V1
- [BugFix] Fix docker build cpu-dev image error
- Fix test_max_model_len in tests/entrypoints/llm/test_generate.py
- Fix Typo in Documentation and Function Name
- [Doc] Fix quantization link titles
- Fix some typo

## Upgrade Command
```bash
python -m pip install 'vllm==0.10.0'
```