# vLLM v0.15.0 — Release & Upgrade Intelligence
- **Product:** vLLM (https://vllm.ai)
- **Version:** v0.15.0
- **Released:** Jan 29, 2026
- **Impact Score:** 7/10
- **Breaking Changes:** Source flagged
- **Canonical Analysis:** https://changelogs.us/vllm/updates/v0.15.0/

## Executive Summary (TL;DR)
vLLM v0.15.0. Source highlight: This release features 335 commits from 158 contributors (39 new)!

## Breaking Changes & Deprecations
- Breaking Changes & Deprecations * **Metrics**: Removed deprecated `vllm:time_per_output_token_seconds` metric - use `vllm:inter_token_latency_seconds` instead (#32661). * **Environment variables**: Removed deprecated environment variables (#32812).

## Improvements
- **Model enhancements**: Voxtral streaming architecture (#32861), SharedFusedMoE for Qwen3MoE (#32082), dynamic resolution for Nemotron Nano VL (#32121), Molmo2 vision backbone quantization (#32385).
- **Model Runner V2**: VLM support (#32546), architecture improvements.
- **Performance**: KV cache offloading redundant load prevention (#29087), FlashAttn attention/cache update separation (#25954).
- **MoE performance**: 1.2-2% E2E throughput improvement via grouped topk kernel fusion (#32058), NVFP4 small-batch decoding improvement (#30885), faster cold start for MoEs with torch.compile (#32805).
- **FP4 kernel optimization**: Up to 65% faster FP4 quantization on Blackwell (SM100F) using 256-bit loads, ~4% E2E throughput improvement (#32520).
- **Kernel improvements**: topk_sigmoid kernel for MoE routing (#31246), atomics reduce counting for SplitK skinny GEMMs (#29843), fused cat+quant for FP8 KV cache in MLA (#32950).

## Bug Fixes
- **WSL**: Platform compatibility fix for Windows Subsystem for Linux (#32749).
- **Speculative decoding**: Eagle draft_model_config fix (#31753).
- **DeepSeek**: DeepSeek-V3.1 + DeepGEMM incompatible scale shapes fix (#32361).
- **Distributed**: DP+MoE inference fix via CpuCommunicator (#31867), P/D with non-MoE DP fix (#33037).
- **EPLB**: Possible deadlock fix (#32418).
- **NIXL**: UCX memory leak fix by exporting UCX_MEM_MMAP_HOOK_MODE=none (#32181).

## Upgrade Command
```bash
python -m pip install 'vllm==0.15.0'
```