16 posts
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.
Since v0.1 Iris, vLLM Semantic Router has made a large jump. In one release cycle, the project rebuilt its model stack, expanded routing into safety, semantic caching, memory, retrieval, and...
We are working on building the System Level Intelligence for Mixture-of-Models (MoM), bringing Collective Intelligence into LLM systems.
vLLM Semantic Router is the System Level Intelligence for Mixture-of-Models (MoM), bringing Collective Intelligence into LLM systems. It lives between users and models, capturing signals from...
As a passionate vLLM community member who wants to see vLLM thrive and reach even more developers, I'm excited to announce vLLM Playground – a modern, feature-rich web interface for managing and...
We are thrilled to announce a major performance update for vLLM-Omni.
Over the past several months, AMD and the vLLM SR Team have been collaborating to bring vLLM Semantic Router (VSR) to AMD GPUs—not just as a performance optimization, but as a fundamental shift in...
Your LLM just called a tool, received accurate data, and still got the answer wrong. Welcome to the world of extrinsic hallucination—where models confidently ignore the ground truth sitting right...
- Speculative decoding serves as an optimization to improve inference performance; however, training a unique draft model for each LLM can be difficult and time-consuming, while production-ready...
Achieve faster, more efficient LLM serving without sacrificing accuracy!
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.
The earlier versions of vLLM Semantic Router relied on classification-based routing, a straightforward approach where user queries are classified into one of 14 MMLU domain categories, and then...
Semantic routing systems face a scaling challenge. When each classification request requires running multiple fine-tuned models independently, the computational cost grows linearly with the number...
Over the past year, hybrid reasoning and automatic routing have increasingly defined progress in large-model infrastructure—shifting the debate from raw scale to per-token efficiency, latency...
Today, we are excited to announce vllm-project/aibrix: a battery-included vLLM Kubernetes serving stack developed by Bytedance. Started in early 2024, AIBrix has been successfully deployed to...
- vLLM boasts the largest open-source community, but what does it take to transform vLLM from the best single-node LLM engine to a premier LLM serving system? - Today, we release “vLLM...
