Run Highly Efficient and Accurate Multi-Agent AI with NVIDIA Nemotron 3 Super Using vLLM
·5 min read
We are excited to support the newly released NVIDIA Nemotron 3 Super model on vLLM.
#model-support
14 posts
Run Highly Efficient and Accurate AI Agents with NVIDIA Nemotron 3 Nano on vLLM
·5 min read
Jan 28th Update: NVIDIA just released their Nemotron 3 Nano model in NVFP4 precision. This model is supported by vLLM out of the box and it uses a new method called Quantization-Aware Distillation...
Run Multimodal Reasoning Agents with NVIDIA Nemotron on vLLM
·4 min read
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.
Chasing 100% Accuracy: A Deep Dive into Debugging Kimi K2's Tool-Calling on vLLM
·11 min read
TL;DR: For best compatibility with vLLM, use Kimi K2 models whose chat templates were updated after commit 94a4053eb8863059dd8afc00937f054e1365abbd (Kimi-K2-0905) or commit...
Now Serving NVIDIA Nemotron with vLLM
·5 min read
Agentic AI systems, capable of reasoning, planning, and taking autonomous actions, are powering the next leap in developer applications. To build these systems, developers need tools that are...
DeepSeek-V3.2-Exp in vLLM: Fine-Grained Sparse Attention in Action
·8 min read
We are excited to announce Day 0 support for DeepSeek-V3.2-Exp, featuring DeepSeek Sparse Attention (DSA) (paper) designed for long context tasks. In this post, we showcase how to use this model...
vLLM Now Supports Qwen3-Next: Hybrid Architecture with Extreme Efficiency
·3 min read
We’re excited to announce that vLLM now supports Qwen3-Next, the latest generation of foundation models from the Qwen team. Qwen3-Next introduces a hybrid architecture with extreme efficiency for...
GLM-4.5 Meets vLLM: Built for Intelligent Agents
·4 min read
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...
vLLM Now Supports gpt-oss
·5 min read
We're thrilled to announce that vLLM now supports gpt-oss on NVIDIA Blackwell and Hopper GPUs, as well as AMD MI300x and MI355x GPUs. In this blog post, we’ll explore the efficient model...
MiniMax-M1 Hybrid Architecture Meets vLLM: Long Context, Fast Inference
·6 min read
This article explores how MiniMax-M1's hybrid architecture is efficiently supported in vLLM. We discuss the model's unique features, the challenges of efficient inference, and the technical...
Transformers modeling backend integration in vLLM
·6 min read
The Hugging Face Transformers library offers a flexible, unified interface to a vast ecosystem of model architectures. From research to fine-tuning on custom dataset, Transformers is the go-to...
Llama 4 in vLLM
·4 min read
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...
Introducing vLLM Inference Provider in Llama Stack
·8 min read
We are excited to announce that vLLM inference provider is now available in Llama Stack through the collaboration between the Red Hat AI Engineering team and the Llama Stack team from Meta. This...
Announcing Llama 3.1 Support in vLLM
·6 min read
Today, the vLLM team is excited to partner with Meta to announce the support for the Llama 3.1 model series. Llama 3.1 comes with exciting new features with longer context length (up to 128K...