Meta is back with Muse Glimmer: local, agentic, multimodal, and open source

DiffusionGemma: 4x faster text generation

Inkling: Our Open-Weights Model

vLLM v0.20.0

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…

Adds Hy4-Preview, VibeVoice, and NeoMME models

Release v5.17.0 New Model additions HYV4 Hy4-Preview is a 780B-parameter mixture-of-experts language model that activates 49B parameters per token. Each MoE layer holds 256 routed experts plus one always-active shared…

Adds Qwen4-Exp and Granite Speech 5.0 models

Release v5.16.0 New Model additions Qwen4-Exp Qwen4-Exp builds on Qwen3.5's hybrid text and multimodal architecture with three key components: GatedResidual (GR), Qwen Sparse Attention (QSA), and Per-Layer Embedding…

Adds Kimi K2.5, MiMo-V2-Flash, and Nemotron 3.5 ASR models

Release v5.13.0 New Model additions KimiK 2.5, 2.6, and 2.7 This release includes the architecture for Kimi 2.5 which is used by 2.5-2.7: Kimi K2.5 is an open-source, native multimodal agentic model that advances…