# vLLM v0.18.0 — Release & Upgrade Intelligence
- **Product:** vLLM (https://vllm.ai)
- **Version:** v0.18.0
- **Released:** Mar 20, 2026
- **Impact Score:** 7/10
- **Breaking Changes:** Source flagged
- **Canonical Analysis:** https://changelogs.us/vllm/updates/v0.18.0/

## Executive Summary (TL;DR)
vLLM v0.18.0. Source highlight: Degraded accuracy when serving Qwen3.5 with FP8 KV cache on B200 (#37618)

## Breaking Changes & Deprecations
- Breaking Changes 1. **Ray no longer a default dependency** — install explicitly if needed (#36170). 2. **Deprecated items removed** — items deprecated in v0.18 have been removed (#36470, #36006).

## Improvements
- **gRPC Serving Support**: vLLM now supports gRPC serving via the new `--grpc` flag (#36169), enabling high-performance RPC-based serving alongside the existing HTTP/REST interface.
- **KV Cache Offloading Improvements**: Smart CPU offloading that stores only frequently-reused blocks (#35342), plus FlexKV as a new offloading backend (#34328) and support for multiple KV groups in offloading spec (#36610).
- **FlashInfer 0.6.6**: Updated FlashInfer dependency (#36768) with numerous performance and correctness improvements.
- **Performance**: Qwen3 Next fused GDN kernel (#35777), LFM2 tuned H100 MoE configs (#36699).
- **NVIDIA**: FA4 for MLA prefill (#34732), DeepSeek-V3.2 MLA kernel optimizations (#34917, #35290).
- **Intel XPU**: Model Runner V2 enabled (#36078), MLA Sparse backend for DeepSeek V3.2 (#33230), LoRA via torch.compile (#36962), block FP8 MoE fallback (#36458), deepseek_scaling_rope fused kernel (#36612).

## Bug Fixes
- If you previously ran into `CUBLAS_STATUS_INVALID_VALUE` and had to use a workaround in `v0.17.0`, you can reinstall `torch 2.10.0`. PyTorch published an updated wheel that addresses this bug.
- **Fixes**: DeepSeek-V3.2 tokenizer space stripping (#37004), Qwen3.5 tool calling (#36774), Qwen3-VL timestamp mismatch (#36136), Qwen3-Next TP>1 weight sharding (#36242), Qwen3-ASR torch.compile (#35869), MiniCPM-V audio inference (#36751), MiniCPM-O 4.5 ViT attention (#34127), routed experts for hybrid models (#35744), Qwen2.5-Omni/Qwen3-Omni multi-video audio_in_video (#37147), DeepSeek-OCR empty images crash (#36670).
- **Model Runner V2**: Probabilistic rejection sampling for spec decode (#35461), pooling models (#36019), extensible CUDA graph dispatch (#35959), WhisperModelState (#35790), XD-RoPE (#36817), model_state CUDA graph capture (#36544).
- **KV cache offloading**: Reuse-frequency-gated CPU stores (#35342), FlexKV offloading backend (#34328), multiple KV groups (#36610), async scheduling fix (#33881).
- **Performance**: Remove busy loop from idle buffer readers (#28053), 2.7% E2E throughput for pooling via worker-side maxsim (#36159), 3.2% via batched maxsim (#36710), CUDA graph memory accounting during profiling (#30515), checkpoint prefetch to OS page cache (#36012), InstantTensor weight loader (#36139), sporadic stall fix via pin_memory removal (#37006).
- **Stability**: VLM concurrent throughput degradation fix (#36557), DP deadlock fix (#35194), DeepSeek V3.2 OOM during CG profiling (#36691), Ray DP startup crash (#36665), NCCL rank calculation fix (#36940), zero-init MLA output buffers for NaN prevention (#37442), CUDA OOM fix (#35594).

## Upgrade Command
```bash
python -m pip install 'vllm==0.18.0'
```