# vLLM v0.22.0 — Release & Upgrade Intelligence
- **Product:** vLLM (https://vllm.ai)
- **Version:** v0.22.0
- **Released:** May 29, 2026
- **Impact Score:** 5/10
- **Breaking Changes:** Not verified
- **Canonical Analysis:** https://changelogs.us/vllm/updates/v0.22.0/

## Executive Summary (TL;DR)
vLLM v0.22.0. Source highlight: This release features 459 commits from 230 contributors (63 new)!

## Improvements
- **Batch invariance, faster**: Batch-invariant inference gained Cutlass FP8 support for a **28.9% end-to-end latency improvement** (#40408), compile-mode support on SM80 (#42456), and an NVFP4 Cutlass linear path (#39912).
- **NVIDIA Blackwell / SM12x**: FlashInfer b12x MoE + FP4 GEMM for SM120/121 (#40082), per-tensor FP8 CUTLASS on SM12.1 (#41215), `head_dim=512` for FlashInfer TRTLLM attention (#38822), FlashInfer Blackwell GDN prefill (#40717), GDN prefill kernel for SM100 (#43273).
- **Performance**: batch-invariant Cutlass FP8 (+28.9% E2E) (#40408), CutlassFP8 padding pre-processing (+13.5% TTFT) (#42651), padded NVFP4 quant kernel (+2.4–5.7% E2E) (#42774), GPU<->CPU sync elimination 1/n (#41429) and 4/n (#42347), fused RoPE+KVCache+q_concat for MLA (#40392), MLA `compute_prefill_context` / `_v_up_proj` optimizations (#42460, #42561), penalties Triton kernel (#40657), `do_not_specialize` in fused FP8 RoPE (#42849), FULL CUDA graph capture for TRITON_MLA decode (#42885).
- **CPU / RISC-V**: RVV-optimized attention kernels for RISC-V Vector Extension (#40119) with VLEN=256 (#42943), fused GDN for AMX CPU (#42707), MXFP4 W4A16 MoE (#41922), experimental Triton + MRv2 on CPU (#43225), improved CPU thread utilization (#42666), `--cpu-distributed-timeout-seconds` (#42968).
- **Intel XPU**: GPTQ int4 support (#37844), mxfp8 MoE (#41918), FP8 block-scaled quantization (#42952), custom-op collective behavior (#41354), multiple sparse-attention kernels (#37888), MoE topk routing + MXFP4 fallback (#42951), CT W4A4 MXFP4 path (#38896), reduced XPU MoE host overhead (#42915).
- **Kernel ABI**: continued migration to libtorch stable ABI — 5/n (#42339), 6/n (#42663), 7/n (#43209).

## Bug Fixes
- **DeepSeek V4 maturity**: DeepSeek V4 received a major hardening pass this cycle — the model was reorganized into a dedicated `vllm/models/deepseek_v4/` package (#43004, #43039, #43073, #43077, #43149), gained NVFP4 fused MoE support (#42209), full + piecewise CUDA graph (#42604), and MTP speculative decoding (#43385). A large set of fused kernels (MegaMoE, `mhc`, Q-norm, indexer, sparse MLA) and ROCm parity fixes landed alongside accuracy fixes (#42810, #43710).
- **Model Runner V2 advances toward default**: MRv2 is now default for Qwen3 dense models. vLLM will fall back to MRv1 for features that aren't yet supported in MRv2 (#39337). sleep-mode weight reload (#42673), `update_config` (#42783), and shared KV-cache layers (#35045), plus many correctness fixes.
- Qwen3.5/3.6: GDN output-projection flatten (#42311), GatedDeltaNet Marlin TP≥2 fix (#36329), ViT full CUDA graph (#42151), runai-streamer weight loading for Qwen3.5/MTP/Qwen3-VL (#42521, #42716), KDA chunk-prefill exp2 semantics (#43195).
- Gemma3/Gemma4: mixed-resolution image co-batching crash fix (#42217), MoE routing closure fix (#42250), tool-parser float-corruption fix (#42128), batched vision encoder for image/video (#43169), multi-GPU fix (#42630).
- Kimi-K2.5: skip vision-tower dtype conversion under quantization (#42869), `mm_projector` dtype fix (#42081).
- Model Runner V2: Qwen3-dense-by-default oracle (#39337), sleep-mode reload weights (#42673), `update_config` (#42783), shared KV-cache layers (#35045), FP32 gumbel sampling (#41775), auto-fallback to MRv1 with connectors (#42955), `logprob_token_ids` correctness (#43125, #41761), prompt-logprobs size fix (#42778).

## Upgrade Command
```bash
python -m pip install 'vllm==0.22.0'
```