Whisper

This release significantly enhances performance for Qwen and GLM models with MTP, introduces new local media APIs, and improves audio capabilities. It also brings numerous bug fixes and performance optimizations across various features like MLX inference and chat functionalities.

This release introduces significant performance improvements for Qwen and GLM models with MTP enabled by default, alongside new local media APIs for video and audio, and enhanced MLX inference on Apple Silicon. It also includes numerous bug fixes and reliability upgrades across various features like chat, training, and hardware support.

This release introduces major new capabilities including support for multimodal Gemma 3n models and Text-to-Speech fine-tuning, alongside new quantization methods (Dynamic 2.0 GGUFs) and support for DeepSeek-R1-0528 and Magistral-24B.

vLLM v0.25.0 introduces Model Runner V2 as the default for dense models, significantly improving performance and adding support for new features like EVS and realtime embeddings. The release also deprecates PagedAttention and enhances the Transformers backend to match native vLLM speed, alongside numerous model additions and performance optimizations across various hardware platforms.

vLLM 0.10.2 introduces native aarch64 support, PyTorch 2.8.0 integration, and extensive optimizations for NVIDIA Blackwell GPUs. It expands model support to include Whisper and various vision-language models while maturing the V1 engine core.

This hotfix release addresses issues from the yanked v5.10.0, introduces several new multimodal and specialized models (Gemma4 Unified, Sapiens2, DeepSeek-OCR-2, Mellum), and includes significant fixes for model parallelism and quantization.