11 posts
We are excited to announce that AutoRound — Intel's state-of-the-art post-training quantization (PTQ) algorithm — is now fully integrated into vLLM-Omni, enabling a streamlined quantize-once,...
We are excited to announce the pre-release of VeRL-Omni, a general reinforcement learning (RL) post-training framework focused on multimodal generative models, built on top of verl and vllm-omni.
Large language model inference has traditionally operated on a simple premise: the user submits a complete prompt (request), the model processes it, and returns a response (either streaming or at...
We are thrilled to announce a major performance update for vLLM-Omni.
Modern Large Multimodal Models (LMMs) introduce a unique serving-time bottleneck: before any text generation can begin, all images must be processed by a visual encoder (e.g., ViT). This encoder...
We are excited to announce the official release of vLLM-Omni, a major extension of the vLLM ecosystem designed to support the next generation of AI: omni-modality models.
Introducing Shared Memory IPC Caching — a high-performance caching mechanism contributed by Cohere to the vLLM project. By bypassing redundant inter-process communication and keeping large...
We are excited to release NVIDIA Nemotron Nano 2 VL, supported by vLLM. This open vision language model (VLM) is built for video understanding and document intelligence.
Until recently, generative AI infrastructure has been tightly coupled with autoregressive text generation models that produce output token-by-token, typically in the form of natural language. vLLM...
General Language Model (GLM) is a family of foundation models created by Zhipu.ai (now renamed to Z.ai). The GLM team has long-term collaboration with vLLM team, dating back to the early days of...
We're excited to announce that vLLM now supports the Llama 4 herd of models: Scout (17B-16E) and Maverick (17B-128E). You can run these powerful long-context, natively multi-modal (up to 8-10...
