vLLM Release 25.10

The NVIDIA vLLM Release 25.10 is made up of two container images available on NGC: vLLM.

Contents of the vLLM container

This container image contains the complete source of the version of vLLM in /opt/vllm. It is pre-built and installed in the default system Python environment (/usr/local/lib/python3.12/dist-packages/vllm) in the container image. Visit vLLM Docs to learn more about vLLM.

The NVIDIA vLLM Container is optimized for use with NVIDIA GPUs, and contains the following software for GPU acceleration

• vLLM: 0.10.2
• flashinfer 0.4.0
• transformers 4.56.1
• flash-attention 2.7.4
• xgrammer 0.1.24
• NVIDIA PyTorch 25.09

Driver Requirements

Release 25.10 is based on CUDA 13.0.2. For comprehensive and up-to-date driver compatibility information, please refer to the following documentation:

• NVIDIA CUDA Compatibility Guide - Compatibility information between CUDA versions and driver releases
• CUDA Toolkit Release Notes - Driver version requirements and compatibility matrices
• NVIDIA Drivers Download - Latest NVIDIA drivers

Key Features and Enhancements

This vLLM release includes the following key features and enhancements.

• Support for openai/gpt-oss-20b and openai/gpt-oss-120b

Announcements

• None.

Known Issues

• vllm serve uses aggressive GPU memory allocation by default (effectively --gpu-memory-utilization≈1.0). On systems with shared/unified GPU memory (e.g. DGX Spark or Jetson platforms), this can lead to out-of-memory errors. If you encounter OOM, start vllm serve with a lower utilization value, for example: vllm serve <model> --gpu-memory-utilization 0.7.