# vLLM v0.14.0 — Release & Upgrade Intelligence
- **Product:** vLLM (https://vllm.ai)
- **Version:** v0.14.0
- **Released:** Jan 20, 2026
- **Impact Score:** 7/10
- **Breaking Changes:** Source flagged
- **Canonical Analysis:** https://changelogs.us/vllm/updates/v0.14.0/

## Executive Summary (TL;DR)
vLLM v0.14.0. Source highlight: **Breaking Changes:**

## Breaking Changes & Deprecations
- Breaking Changes:** - **Async scheduling is now enabled by default** - Users who experience issues can disable with `--no-async-scheduling`. - Excludes some not-yet-supported configurations: pipeline parallel, CPU backend, non-MTP/Eagle spec decoding.

## Improvements
- **Async scheduling enabled by default** (#27614): Overlaps engine core scheduling with GPU execution, improving throughput without user configuration. Now also works with speculative decoding (#31998) and structured outputs (#29821).
- **Model Runner V2 enhancements**: UVA block tables (#31965), M-RoPE (#32143), `logit_bias`/`allowed_token_ids`/`min_tokens` support (#32163).
- 2.9% throughput + 10.8% TTFT via fill(0) optimization (#31754)
- 5.3% throughput + 2.2% TTFT via problem size calculation (#31830)
- Fused SiLU+Mul+Quant for NVFP4 (#31832)
- NVFP4 stride fusion (#31837)

## Bug Fixes
- Invalid UTF-8 tokens (#28874)
- CPU RoPE gibberish with `--enforce-eager` (#31643)
- Tool call streaming finish chunk (#31438)
- Encoder cache leak CPU scheduling stuck (#31857)
- Engine crash: tools + response_format (#32127)
- Voxtral transcription API (#31388)

## Upgrade Command
```bash
python -m pip install 'vllm==0.14.0'
```