vLLM changelog

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 pref

This is a patch release on top of v0.27.0. Support quantized DSpark Markov heads (#50424)

vLLM v0.27.0 Release Notes Highlights This release features 561 commits from 242 contributors (64 new)! Kimi K3 support with a full stack landing in one release: core model files and kernels (#50089, #50000), Python (#50093) and Rust (#5010

vLLM v0.26.0 Release Notes Highlights This release features 411 commits from 212 contributors (61 new)! New Inkling model family with a full support stack: base modeling (#48799), piecewise CUDA graph support (#48822), Hopper FA4 relative a

vLLM v0.25.1 Highlights This release features 2 commits from 2 contributors (1 new)! v0.25.1 is a patch release containing two targeted bug fixes on top of v0.25.0. Bug Fixes Avoid blocking model launching when no system FFmpeg is available

vLLM v0.25.0 Release Notes Highlights This release features 558 commits from 232 contributors (64 new)! Model Runner V2 is now the default for all dense models (#44443). Building on quantized-model support from the previous release, MRv2 is

vLLM v0.24.0 Release Notes Highlights This release features 571 commits from 256 contributors (77 new)! MiniMax-M3: Added support for the new MiniMax-M3 model (#45381), with a fast follow-on of BF16/FP8 indexer via MSA (#45892), MXFP4 suppo

vLLM v0.23.0 Release Notes Please note that Minimax M3 is not yet supported in this version. Please follow vLLM recipe for usage guides for M3. Highlights This release features 408 commits from 200 contributors (63 new)! DeepSeek-V4 matures

Highlights This release features 8 commits from 6 contributors (1 new)! v0.22.1 is a patch release on top of v0.22.0 with targeted bug fixes plus a couple of additions: new model support for JetBrains' Mellum v2, zentorch-accelerated quanti

Highlights This release features 459 commits from 230 contributors (63 new)! 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,

Highlights This release features 367 commits from 202 contributors (49 new)! Transformers v4 deprecated: This release formally deprecates transformers v4 support (#40389). Users should migrate to transformers v5. C++20 build requirement: vL

vLLM v0.20.2 Highlights This release features 6 commits from 6 contributors (0 new)! This is a small patch release with bug fixes for DeepSeek V4, gpt-oss, and Qwen3-VL Bug Fixes DeepSeek V4 sparse attention: Re-enable the persistent topk p

vLLM v0.20.1 This is a patch release on top of v0.20.0 primarily focused on DeepSeek V4 stabilization and performance improvements, along with several important bug fixes. DeepSeek V4 Base model support (#41006). Multi-stream pre-attention

vLLM v0.20.0 Highlights This release features 752 commits from 320 contributors (123 new)! DeepSeek V4: Initial DeepSeek V4 support landed (#40860), with DSML token-leakage fix in DSV4/3.2 (#40806), DSA + MTP IMA fix (#40772), and a silu cl

This is a patch release on top of v0.19.0 with Transformers v5.5.3 upgrade and bug fixes for Gemma4: Update to transformers v5 (#30566) [Bugfix] Fix invalid JSON in Gemma 4 streaming tool calls by stripping partial delimiters (#38992) [Bugf

vLLM v0.19.0 Highlights This release features 448 commits from 197 contributors (54 new)! Gemma 4 support: Full Google Gemma 4 architecture support including MoE, multimodal, reasoning, and tool-use capabilities (#38826, #38847). Requires t

This is a patch release on top of v0.18.0 to address a few issues: Change default SM100 MLA prefill backend back to TRT-LLM (#38562) Fix mock.patch resolution failure for standalone_compile.FakeTensorMode on Python <= 3.10 (#37158) Disable

vLLM v0.18.0 Known issues Degraded accuracy when serving Qwen3.5 with FP8 KV cache on B200 (#37618) 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 publi

This is a patch release on top of v0.17.0 to address a few issues: New Model: Nemotron 3 Super Fix passing of activation_type to trtllm fused MoE NVFP4 and FP8 (#36017) Fix/resupport nongated fused moe triton (#36412) Re-enable EP for trtll

vLLM v0.17.0 Known Issue: If you are on CUDA 12.9+ and encounter a CUBLAS_STATUS_INVALID_VALUE error, this is caused by a CUDA library mismatch. To resolve, try one of the following: Remove the path to system CUDA shared library files (e.g.

vLLM v0.16.0 Please note that this release was branch cut on Feb 8, so any features added to vLLM after that date is not included. Highlights This release features 440 commits from 203 contributors (7 new)! Async scheduling + Pipeline Paral

is a patch release with security fixes, RTX Blackwell GPU fixes support, and bug fixes. Security CVE-2025-69223: Updated aiohttp dependency (#33621) CVE-2026-0994: Updated Protobuf dependency (#33619) Highlights Bugfix Hardware Support RTX

Highlights This release features 335 commits from 158 contributors (39 new)! Model Support New architectures: Kimi-K2.5 (#33131), Molmo2 (#30997), Step3vl 10B (#32329), Step1 (#32511), GLM-Lite (#31386), Eagle2.5-8B VLM (#32456). LoRA expan

This is a patch release on top of v0.14.0 to address a few security and memory leak fixes.

Highlights This release features approximately 660 commits from 251 contributors (86 new contributors). Breaking Changes: Async scheduling is now enabled by default - Users who experience issues can disable with --no-async-scheduling. Exclu

vLLM v0.13.0 Release Notes Highlights Highlights This release features 442 commits from 207 contributors (61 new contributors)! Breaking Changes: This release includes deprecation removals, PassConfig flag renames, and attention configurati

vLLM v0.12.0 Release Notes Highlights Highlights This release features 474 commits from 213 contributors (57 new)！ Breaking Changes: This release includes PyTorch 2.9.0 upgrade (CUDA 12.9), V0 deprecations including xformers backend, and sc

This release includes 4 bug fixes on top of v0.11.1: [BugFix] Ray with multiple nodes (https://github.com/vllm-project/vllm/pull/28873) [BugFix] Fix false assertion with spec-decode=[2,4,..] and TP>2 (https://github.com/vllm-project/vllm/pu

Highlights This release includes 1456 commits from 449 contributors (184 new contributors)! Key changes include: PyTorch 2.9.0 + CUDA 12.9.1: Updated the default CUDA build to torch==2.9.0+cu129, enabling Inductor partitioning and landing m

Highlights This release features 538 commits, 207 contributors (65 new contributors)! This release completes the removal of V0 engine. V0 engine code including AsyncLLMEngine, LLMEngine, MQLLMEngine, all attention backends, and related comp

Highlights This release contains 740 commits from 266 contributors (97 new)! Breaking Changes: This release includes PyTorch 2.8.0 upgrade, V0 deprecations, and API changes - please review the changelog carefully. aarch64 support: This rele

This is a critical bugfix and security release: Fix CUTLASS MLA Full CUDAGraph (#23200) Limit HTTP header count and size (#23267): https://github.com/vllm-project/vllm/security/advisories/GHSA-rxc4-3w6r-4v47 Do not use eval() to convert unk

Highlights v0.10.1 release includes 727 commits, 245 committers (105 new contributors). NOTE: This release deprecates V0 FA3 support and as a result FP8 kv-cache in V0 may have issues Model Support New model families: GPT-OSS with comprehen

Highlights v0.10.0 release includes 308 commits, 168 contributors (62 new!). NOTE: This release begins the cleanup of V0 engine codebase. We have removed V0 CPU/XPU/TPU/HPU backends (#20412), long context LoRA (#21169), Prompt Adapters (#20

Highlights This release contains 452 commits from 167 contributors (31 new!) NOTE: This is the last version where V0 engine code and features stay intact. We highly recommend migrating to V1 engine. Engine Core Priority Scheduling is now im

Highlights This release features 274 commits, from 123 contributors (27 new contributors!) Progress in large scale serving DP Attention + Expert Parallelism: CUDA graph support (#18724), DeepEP dispatch-combine kernel (#18434), batched/mask

This patch release contains important bugfix for DeepSeek family of models on NVIDIA Ampere and below (#18807)

Highlights This release features 649 commits, from 215 contributors (82 new contributors!) vLLM has upgraded to PyTorch 2.7! (#16859) This is a breaking change for environment dependency. The default wheel has been upgraded from CUDA 12.4 t

This post release contains two bug fix for memory leak and model accuracy Fix Memory Leak in _cached_reqs_data (#17567) Fix sliding window attention in V1 giving incorrect results (#17574)

This release contains 310 commits from 143 contributors (55 new contributors!). Highlights This release features important multi-modal bug fixes, day 0 support for Qwen3, and xgrammar's structure tag feature for tool calling. Model Support

This release contains 180 commits from 84 contributors (25 new contributors!). Highlights This release includes important accuracy fixes for Llama4 models, if you are using it, we highly recommend you to update. Model Llama4 (#16113,#16509)

Highlights This release features 260 commits, 109 contributors, 38 new contributors. We are excited to announce Day 0 Support for Llama 4 Scout and Maverick (#16104). Please see our blog for detailed user guide. Please note that Llama4 is o

This release contains important bug fix for the V1 engine's memory usage. We highly recommend you upgrading! Highlights Revert "Use uv python for docker rather than ppa:deadsnakess/ppa (#13569)" (#15377) Remove openvino support in favor of

This release contains important bug fixes for v0.8.0. We highly recommend upgrading! V1 Fixes Ensure using int64 for sampled token ids (#15065) Fix long dtype in topk sampling (#15049) Refactor Structured Output for multiple backends (#1469

featured 523 commits from 166 total contributors (68 new contributors)! Highlights V1 We have now enabled V1 engine by default (#13726) for supported use cases. Please refer to V1 user guide for more detail. We expect better performance for

Highlights 🎉 253 commits from 93 contributors, including 29 new contributors! Deepseek enhancements: Support for DeepSeek Multi-Token Prediction, 1.69x speedup in low QPS scenarios (#12755) AMD support: DeepSeek tunings, yielding 17% laten

Highlights Qwen2.5-VL is now supported in vLLM. Please note that it requires a source installation from Hugging Face transformers library at the moment (#12604) Add transformers backend support via --model-impl=transformers. This allows vLL

Highlights This release features MLA optimization for Deepseek family of models. Compared to v0.7.0 released this Monday, we offer ~3x the generation throughput, ~10x the memory capacity for tokens, and horizontal context scalability with p

Highlights vLLM's V1 engine is ready for testing! This is a rewritten engine designed for performance and architectural simplicity. You can turn it on by setting environment variable VLLM_USE_V1=1. See our blog for more details. (44 commits

This release restore functionalities for other quantized MoEs, which was introduced as part of initial DeepSeek V3 support 🙇 . What's Changed [Docs] Document Deepseek V3 support by @simon-mo in https://github.com/vllm-project/vllm/pull/115

Highlights Support Deepseek V3 (#11523, #11502) model. On 8xH200s or MI300x: vllm serve deepseek-ai/DeepSeek-V3 --tensor-parallel-size 8 --trust-remote-code --max-model-len 8192. The context length can be increased to about 32K beyond runni

Highlights Significant progress on the V1 engine refactor and multimodal support: New model executable interfaces for text-only and multimodal models, multiprocessing, improved configuration handling, and profiling enhancements (#10374, #10

This patch release covers bug fixes (#10347, #10349, #10348, #10352, #10363), keep compatibility for vLLMConfig usage in out of tree models (#10356) What's Changed Add default value to avoid Falcon crash (#5363) by @wchen61 in https://githu

Highlights Significant progress in V1 engine core refactor (#9826, #10135, #10288, #10211, #10225, #10228, #10268, #9954, #10272, #9971, #10224, #10166, #9289, #10058, #9888, #9972, #10059, #9945, #9679, #9871, #10227, #10245, #9629, #10097

Highlights New Models Support Ministral 3B and Ministral 8B via interleaved attention (#9414) Support multiple and interleaved images for Llama3.2 (#9095) Support VLM2Vec, the first multimodal embedding model in vLLM (#9303) Important bug f

Highlights Model Support New Models: Text: Granite MoE (#8206), Mamba (#6484, #8533) Vision: GLM-4V (#9242), Molmo (#9016), NVLM-D (#9045) Reward model support: Qwen2.5-Math-RM-72B (#8896) Expansion in functionality: Add Gemma2 embedding mo

Highlights Model Support Support Llama 3.2 models (#8811, #8822) vllm serve meta-llama/Llama-3.2-11B-Vision-Instruct --enforce-eager --max-num-seqs 16 Beam search have been soft deprecated. We are moving towards a version of beam search tha

Highlights This release contains an important bugfix related to token streaming combined with stop string (#8468) What's Changed [CI/Build] Enable InternVL2 PP test only on single node by @Isotr0py in https://github.com/vllm-project/vllm/pu

Highlights This release features important bug fixes and enhancements for Pixtral models. (#8415, #8425, #8399, #8431) Chunked scheduling has been turned off for vision models. Please replace --max_num_batched_tokens 16384 with --max-model-

Highlights Model Support Added support for Pixtral (mistralai/Pixtral-12B-2409). (#8377, #8168) Added support for Llava-Next-Video (#7559), Qwen-VL (#8029), Qwen2-VL (#7905) Multi-input support for LLaVA (#8238), InternVL2 models (#8201) Pe