# vLLM v0.29.0 — Release & Upgrade Intelligence
- **Product:** vLLM (https://vllm.ai)
- **Version:** v0.29.0
- **Released:** Sep 09, 2026
- **Impact Score:** 7/10
- **Breaking Changes:** Source flagged
- **Canonical Analysis:** https://changelogs.us/vllm/updates/v0.29.0/

## Executive Summary (TL;DR)
vLLM v0.29.0. Source highlight: This release features 594 commits from 277 contributors (91 new)!

## Breaking Changes & Deprecations
- Breaking changes**: ten deprecated model architectures removed (#53608); FlexOlmo, Olmo3 and Hunyuan V1/VL migrated to the Transformers modeling backend (#53615); PyAV video decoder backend removed (#54231); `python -m vllm.entrypoints.openai.api_server` deprecated in favor of `vllm serve` (#52131); `VLLM_TEST_FORCE_FP8_MARLIN` (#52182) and `VLLM_ROCM_USE_AITER_FP4_ASM_GEMM` (#53141) removed.
- Breaking Changes & Deprecations * Ten deprecated architectures removed: Arctic, Chameleon, Cheers, Fairseq2Llama, FireRedLID, GritLM, HCXVision, MPT, the `RWForCausalLM` and `StableLMEpochForCausalLM` aliases, and `PrithviGeoSpatialMAE` (superseded by `Terratorch`) (#53608). * FlexOlmo, Olmo3, Hunyuan V1 and Hunyuan VL are now served through the Transformers modeling backend (#53615).

## New Features
- InstantTensor added to CUDA dependencies; the loader is not enabled by default (#52801). CuPy constraint relaxed to exclude only 14.1.0 (#44284).

## Improvements
- **Mamba prefix caching**: internal prefill checkpoints deliver a 9%-25% TTFT improvement (#52789); `prefix_cache_retention_interval` is now a CLI argument defaulting to 0 (#52216), with dense retention automatically restored for hybrid models using EAGLE/MTP (#55760, #55861).
- **Multimodal performance**: ViT full CUDA graph for Idefics3 and SmolVLM (#47625), packed encoder attention for Pixtral (#52185), fused Kimi vision Q/K RoPE kernel (#50400), Dots3 NOTE runtime (#53517) and Omni encoder optimizations (#53460), MM tensors no longer broadcast to workers for prefix-cache-covered items (#52041), redundant placeholder scans skipped (#52925), common token sequences cached (#53560), async media resolved concurrently across modalities (#54537), and H2D copies pinned to a

## Bug Fixes
- **Model Runner V2 is now the default for all models** (#53183), completing the rollout that began with pooling models (#48290). MRV2 also gained CUDA graph memory profiling for KV cache auto-sizing (#53306), batch-sharded sampling that cuts per-step logits memory by 1/TP (#50465), prompt embeds (#42963), `extract_hidden_states` speculation (#49811), padded FULL cudagraph dispatch for uniform decode under spec decode (#53407), and DP-sync skipping before EAGLE/MTP draft prefill (#53694). MRV1 rem
- **Kimi-K3 and DeepSeek V4 performance**: fused MXFP4 top-k finalization in the K3 latent tail (about 5% E2E latency, #53152), K3 Mamba metadata preparation in one Triton launch (6.6-7.6x kernel speedup, #52388), tuned Hopper low-latency GEMM (#54088) now also dispatched on SM100 (#53534) and used for `eh_proj` (12.9-25.2% kernel speedup, #53942), GEMM-RS extended to GEMM-AR (#53053), MLA gate merged into the QKV-A projection (#54015), K3 DCP with DSpark (#52188) and DCP partial prefix cache hits
- **Transformers modeling backend**: FlexOlmo, Olmo3 and Hunyuan V1/VL migrated off native implementations (#53615), multimodal path hardened (#51827), and `RMSNormFuser.fuse` performance fixed (#52766).
- **LoRA**: DeepSeek V4 (#53361), Qwen3-Omni multimodal LoRA (#52786, #53557), tower/connector LoRA for LLaVA-NeXT (#49788) and LFM2-VL (#51498), plus fixes for Muse-Glimmer (#53513), Qwen3.5 embedding modules (#48850), partial LoRA on Qwen3.5/3.6 GatedDeltaNet (#47640), int32 overflow in punica kernels at long context (#53034), false target matches on unsupported module types (#52313), and base-layer/routed-expert prefix ordering (#52552).
- **Model Runner V2**: default for all models (#53183) and pooling models (#48290), CUDA graph memory reservation (#53306), batch-sharded sampling (#50465), prompt embeds (#42963), `extract_hidden_states` (#49811), padded FULL cudagraph dispatch (#53407), DP-sync skipping for drafts (#53694), decoupled draft/target gumbel noise streams (#54282), encoder-only path split out (#53176), and memory released correctly on shutdown and sleep (#53508, #54246, #54162, #53955, #53682).
- **Speculative decoding**: per-request acceptance stats (#48915), adaptive verification with logprobs (#52242), on SM100 sparse MLA (#52783) and DSv4 + SM90 (#52795), varlen trtllm-gen decode (#52157), FlashInfer MLA for DSpark drafting under DCP (#54277), fused GDN MTP for all Qwen head ratios (#52539), widest uniform decode batch captured by default (#50488) with memory-safe graph sizes (#54418), and fixes for short_conv/LFM2 targets (#50272), speculators-format config overrides (#42376), DFlas

## Upgrade Command
```bash
python -m pip install 'vllm==0.29.0'
```