# vLLM v0.11.1 — Release & Upgrade Intelligence
- **Product:** vLLM (https://vllm.ai)
- **Version:** v0.11.1
- **Released:** Nov 18, 2025
- **Impact Score:** 5/10
- **Breaking Changes:** Not verified
- **Canonical Analysis:** https://changelogs.us/vllm/updates/v0.11.1/

## Executive Summary (TL;DR)
vLLM v0.11.1. Source highlight: Key changes include:

## New Features
- **Anthropic API Support**: Added support for the `/v1/messages` endpoint, allowing users to interact with `vllm serve` using Anthropic-compatible clients.
- [Docs] Add Toronto Meetup (@mgoin #25773)
- [CI] Add E2E Blackwell Quantized MoE Test (@mgoin #25723)
- Add option to restrict media domains (@russellb #25783)
- Add flashinfer-build.sh and register precompiled cu128 wheel in Dockerfile (@mgoin #25782)
- [CI/Build] Add timing to Model Executor Test (@22quinn #25799)

## Improvements
- **Stronger scheduler + KV ecosystem**: Improved test coverage in CI and made scheduler behavior more robust with KV connectors, prefix caching, and multi-node deployments.
- [perf] Use CPU tensor to reduce GPU->CPU sync (@lhtin #25884)
- [Doc] Improve MM Pooling model documentation (@DarkLight1337 #25966)
- [DeepSeek] Improve performance of DS MLA cache kernel (@MatthewBonanni #26132)
- [Perf] Optimize `reshape_and_cache` CUDA Kernel (@ZJY0516 #25955)
- [Perf] Remove hardcoded num_warps=1 (@chelsea0x3b #26183)

## Bug Fixes
- **PyTorch 2.9.0 + CUDA 12.9.1**: Updated the default CUDA build to `torch==2.9.0+cu129`, enabling Inductor partitioning and landing multiple fixes in graph-partition rules and compile-cache integration.
- **Robust async scheduling**: Fixed several correctness and stability issues in async scheduling, especially when combined with chunked prefill, structured outputs, priority scheduling, MTP, and DeepEP / DCP. We expect `--async-scheduling` to be enabled by default in the next release.
- [Bugfix] Improve GLM4 MoE Reasoning Parser's is_reasoning_end Condition (@frankwang28 #25355)
- [CI] Fix FlashInfer AOT in release docker image (@mgoin #25730)
- [Bugfix] Optimize CpuGpuBuffer initialization (@namanlalitnyu #25447)
- [Bugfix] Allow Only SDPA Backend for ViT on B200 for Qwen3-VL (@yewentao256 #25788)

## Upgrade Command
```bash
python -m pip install 'vllm==0.11.1'
```