# vLLM v0.28.0 — Release & Upgrade Intelligence
- **Product:** vLLM (https://vllm.ai)
- **Version:** v0.28.0
- **Released:** Aug 26, 2026
- **Impact Score:** 7/10
- **Breaking Changes:** Source flagged
- **Canonical Analysis:** https://changelogs.us/vllm/updates/v0.28.0/

## Executive Summary (TL;DR)
vLLM v0.28.0. Source highlight: This release features 584 commits from 270 contributors (76 new)!

## Breaking Changes & Deprecations
- Breaking changes**: bitsandbytes support migrated to an out-of-tree plugin (#43529); Transformers bumped to 5.15.0 (#51668); the deprecated `calculate_kv_scales` runtime KV scale calculation was removed (#49389); `override_attention_dtype` was removed (#48684).
- Breaking Changes & Deprecations * bitsandbytes support is now an out-of-tree plugin (#43529). * The deprecated `calculate_kv_scales` runtime KV scale calculation was removed (#49389).
- `reasoning_content` output removal is documented as a breaking client change (#50624).

## Improvements
- **Kimi-K3 performance push**: a major optimization effort for Kimi-K3 across the stack — Decode Context Parallel (DCP) support (#50484), fused FlashKDA decode and prefill kernels (#50654, #51311, #52458), SiTU activation support for MegaMoE (#50510), GEMM-RS for sequence parallelism (#52079), combined all-gathers with 1.5~3x kernel-level speedup (#51070), an adaptive speculative token budget delivering ~60% better DSpark TTFT (#51725), and optional shared-expert sharding saving ~17 GiB of memory
- **Multimodal performance**: fused on-device multimodal preprocess normalization (#50411), faster placeholder and token-match scanning (#50716), and repeated prompt-update scans avoided (#51774).
- **Performance**: continued elimination of GPU<->CPU syncs on the execution path (#51458, #51738, #52369) now guarded by a CI sync check (#43107), new JIT warmup infrastructure with predicate filtering (#49315), the top-k/top-p Triton sampler launched with 8 warps (#51507), detokenization skipped in offline beam search (#50333), Mask Replay (#49577), optimized long-context MLA cache gathers (#51739), and HF revisions resolved to a commit hash once per model load (#49990).
- **NVIDIA**: FlashInfer XQA decode support on SM12x (#49718), a CuTeDSL fused query kernel on SM100 (#49792), programmatic dependent launch for the DSA decode kernels (#50230), the native DSA decode path for MTP=3 on SM90 (#52164), GB10 fused-MoE FP8 tuning configs (#52502), and B12X dense linear backends (#52016).
- **AMD ROCm**: torch 2.12 / triton 3.7 stack bump (#50607), AITER and FP8 inference enabled on GFX120x (#43615), DeepSeek-V4 on gfx11 (#47017), optimized Triton sparse-MLA decode on gfx950 (#52212), FlyDSL decode-attention kernel for 4-bit TurboQuant KV cache (#47896) and an fp8 MQA logits kernel on gfx942 (#49544), a fused Kimi-K3 KDA decode kernel (#50654), fused bf16→fp32 router GEMM (#50268), pinned memory on supported WSL2 kernels (#50126), and preshuffled sparse indexing for 16-token blocks
- **CPU**: an MLA backend so DeepSeek-V2/V3 can run on CPU (#49453), a triton-cpu wheel (#52092), GPTQ and AWQ enabled on s390x (#51148) along with tcmalloc (#50841), BF16 MoE routed through zentorch on AMD (#44201), an unquantized MoE backend for Power (VSX) (#51624), unquantized MoE migrated to the modular-kernel experts structure (#50133), and the MXFP4 block scale folded in 2 instructions instead of 4 (#51583).

## Bug Fixes
- **Qwen**: Qwen3.8 enabled on AMD ROCm (#50068), fused CUDA post-conv MTP decode kernel for Qwen3.5 GDN (#51674), GDN gates aligned with speculative tokens (#51812), and Qwen3.5 fixes for text-only checkpoints (#50734, #50355).
- **KV cache & scheduling**: per-request scheduling for MLA chunked context (#50613), partial-tail prefix reuse with fine-grained prefix matching (#50507), backend-published KV packing in the KV-cache layout refactor (#51612, #51704), LIFO free-block reuse order restored when prefix caching is off (#51482), and silent request skipping in priority scheduling fixed (#49206).
- **RL workflows**: stateful trainer send over NCCL and sparse NCCL (#50902), `CuMemAllocator.discard()` for tag-selective GPU memory release (#52514), level-2 sleep/wake/reload fixed with LoRA enabled (#39935), and rewritten weight-transfer docs with standardized examples (#51729).
- **Startup robustness**: file:// rendezvous for single-node executors eliminates startup port races (#50999, #51652), frontend processes are watched during engine startup (#43417), a `get_open_port()` livelock on DP-reserved ports was fixed (#50965), and NVML is no longer re-initialized on every device-capability check (#50393).
- **Intel XPU**: a torch linear backend including blockwise GEMM (#49664, #50826), MXFP8 linear weights for the INC DeepSeek V4 model (#48476), async-scheduling PP sampled-token broadcast overlapped with compute (#51650), an XPU wheel added to the release pipeline (#52108), tuned Mamba SSU configs for Arc Pro B70 (#50534), and UVA weight offloading fixes (#51770).
- **Parallelism**: EPLB balancedness calculation fixed and tested (#51813), dense multinode DP rescope (#49212).

## Upgrade Command
```bash
python -m pip install 'vllm==0.28.0'
```