Qwen3-VL

This release introduces the Inkling multimodal model and TIPSv2, alongside significant improvements in kernel performance, generation capabilities, and bug fixes across various components. It also includes breaking changes for GPTNeoX and GPTBigCode related to weight remapping and attention backend compatibility.

This release introduces two major new models, DiffusionGemma and DeepSeek-V3.2, alongside significant enhancements to the custom kernel API for better fusion capabilities. Numerous bug fixes address issues across various models, CI stability, and dependency compatibility.

This release introduces support for several next-generation model architectures, including the high-efficiency Qwen3-Next and Qwen3-VL series, the privacy-focused VaultGemma, and the high-speed Longcat Flash MoE.

v0.24.0 introduces extensive support and performance optimizations for new models like MiniMax-M3 and DeepSeek-V4, matures the Model Runner V2 with default quantization support, and overhauls device selection by removing internal use of CUDA_VISIBLE_DEVICES.

vLLM v0.20.2 is a small patch release focused on bug fixes for DeepSeek V4, gpt-oss, and Qwen3-VL models.

v0.18.0 introduces major features like gRPC serving, GPU-less render serving, and significant improvements to KV cache offloading and Elastic Expert Parallelism. Ray is now an optional dependency, and numerous model-specific fixes and kernel optimizations have been integrated.

This release introduces significant feature additions, including support for Qwen3-VL, Krea2, and various partner node model updates. It also includes several quality-of-life improvements like new API endpoints and node enhancements.

This release introduces major performance enhancements with FP8 Reinforcement Learning support and significant VRAM reductions across the board. It also adds support for new models like DeepSeek-OCR and Qwen3-VL, alongside improved Docker integration.