# vLLM v0.28.0

- Product: vLLM (https://whatsnew.fyi/product/vllm)
- Vendor: vLLM
- Date: 2026-08-26
- Version: v0.28.0
- Original notes: https://github.com/vllm-project/vllm/releases/tag/v0.28.0
- Permalink: https://whatsnew.fyi/product/vllm/releases/v0.28.0

What's New is an index, not a publisher: every entry below links to the vendor's own release notes, which are the authoritative source. Entries are labelled where they are hand-curated sample data, pre-releases, or drawn from a secondary source such as a developer blog.

Reuse: the summaries, labels and curation here are © What's New. Quote freely with attribution and a link back; wholesale republication of the corpus is not permitted — terms: https://whatsnew.fyi/terms. The vendors' own release notes remain their publishers'.

---

- **added** — Decode Context Parallel (DCP) support for Kimi-K3
- **added** — Fused FlashKDA decode and prefill kernels for Kimi-K3
- **added** — SiTU activation support for MegaMoE
- **added** — GEMM-RS for sequence parallelism
- **added** — Combined all-gathers optimization with 1.5~3x kernel-level speedup
- **added** — Adaptive speculative token budget delivering ~60% better DSpark TTFT
- **added** — Optional shared-expert sharding saving ~17 GiB of memory per GPU
- **added** — Kimi-K3 support on ROCm with the V2 model runner
- **added** — Sparse MLA end-to-end support for DeepSeek V4 plain decode, MTP, and DSpark speculative decoding
- **added** — AMD Quark NVFP4 support for DeepSeek V4
- **added** — Reasoning-effort prompts and mappings for DeepSeek V4
- **added** — DFlash2 with local convolution and a candidate selector
- **added** — DSpark confidence-scheduled verification
- **added** — Async scheduling auto-enabled for draft models
- **added** — Model Runner V2 E/P/D disaggregation
- **added** — Weight offloading in Model Runner V2
- **added** — Multi-layer MTP KV cache support in Model Runner V2
- **added** — Tiered KV cache offloading with disk offloading support
- **added** — Standalone Rust frontend renderer
- **changed** — Raise max_num_batched_tokens default from 8192 to 16384
- **changed** — Enable prefix caching by default for Mamba models
- **changed** — Raise Blackwell CUDA graph capture default to 1024
- **changed** — Migrate bitsandbytes support to an out-of-tree plugin
- **changed** — Bump Transformers to 5.15.0
- **removed** — Remove deprecated calculate_kv_scales runtime KV scale calculation
- **removed** — Remove override_attention_dtype

#### v0.28.0

##### Highlights

This release features 584 commits from 270 contributors (76 new)!

* **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 per GPU (#50912). Kimi-K3 also now runs on ROCm with the V2 model runner (#51653).
* **DeepSeek V4**: sparse MLA now works end-to-end for plain decode, MTP, and DSpark speculative decoding (#51538), joined by AMD Quark NVFP4 support (#47972), reasoning-effort prompts and mappings (#50580), sparse top-k metadata kernel optimizations (#52084, #51967), narrowed eager CUDA graph regions (#51430, #52401), and ROCm enablement on gfx11 and gfx950 (#47017, #52212).
* **Speculative decoding advances**: DFlash2 with local convolution and a candidate selector (#52816), DSpark confidence-scheduled verification (#47808), and async scheduling auto-enabled for draft models (#48341).
* **Model Runner V2 maturation**: E/P/D disaggregation (#38390), weight offloading (#51413), multi-layer MTP KV cache support (#50062), encoder CUDA graphs (#49852), decoder token-wise pooling (#50931) plus Transformers pooling models (#52425), attention-free models (#52374), and `thinking_token_budget` support (#46727).
* **Tiered KV cache offloading**: disk offloading support (#49644), out-of-tree secondary tier managers via `module_path` (#51007), partial secondary-tier load results (#50321), tiering metrics (#48798), and a canonical CPU layout for parallelism-agnostic offload (#48414).
* **Rust frontend & gRPC**: a standalone renderer (#50289), multimodal image inference over gRPC (#50368), explicit data-parallel rank routing (#51178), and RL lifecycle control (#51316), with protobuf schemas now published to Buf (#51276).
* **New defaults**: `max_num_batched_tokens` raised from 8192 to 16384 (#51726), prefix caching enabled by default for Mamba models (#50991), and the Blackwell CUDA graph capture default raised to 1024 (#49390).
* **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).

##### Release Artifacts

###### Python Wheels

| Platform | Install |
|---|---|
| PyPI (CUDA 13.0) | `pip install vllm` |
| PyPI (CUDA 13.0, uv) | `uv pip install vllm --torch-backend=auto` |
| ROCm | `pip install vllm --extra-index-url https://wheels.vllm.ai/rocm/0.28.0/rocm722` |

###### Docker Images

| Platform | Docker Image |
|---|---|
| CUDA 13.0 (Default) | `docker pull vllm/vllm-openai:v0.28.0` (`v0.28.0-cu130` also works) |
| CUDA 12.9 | `docker pull vllm/vllm-openai:v0.28.0-cu129` |
| CUDA 13.0 + Ubuntu 24.04 | `docker pull vllm/vllm-openai:v0.28.0-ubuntu2404` |
| CUDA 12.9 + Ubuntu 24.04 | `docker pull vllm/vllm-openai:v0.28.0-cu129-ubuntu2404` |
| ROCm | `docker pull vllm/vllm-openai-rocm:v0.28.0` |
| CPU | `docker pull vllm/vllm-openai-cpu:v0.28.0` |
| XPU | `docker pull vllm/vllm-openai-xpu:v0.28.0` |

###### Other Artifacts

Pre-built release artifacts are available in the **Assets** section at the bottom of this page, including:
- Source distribution tarball
- CUDA 12.9 Python wheels for x86_64 and arm64
- CUDA 13.0 Python wheels for x86_64 and arm64
- CPU Python wheels for x86_64, arm64, and macOS

##### Model Support
* **New models**: Muse Glimmer (#51655), Ling 3.0 Flash with BF16, MTP, and parser support (#51045) plus an FP8 variant (#51265) and hybrid MXFP4 routed experts (#52114), Dots3 NOTE native multimodal supp

_[Truncated at 4000 characters — full notes: https://github.com/vllm-project/vllm/releases/tag/v0.28.0]_