← all releases
vLLM·Jul 11, 2025·v0.25.0·open source

vLLM

vLLM is a high-throughput, memory-efficient inference and serving engine for large language models. The v0.25.0 release introduces Model Runner V2 as the default engine for dense models, removes legacy PagedAttention, and adds extensive support for new models, hardware, and performance optimizations. Key technical advancements include improved support for heterogeneous speculative decoding, a new streaming parser engine, and enhanced support for a wide array of architectures such as GLM-5, MiniMax-M3, and various multimodal models.

LLMInference EngineAI InfrastructureOpen Source
overview

vLLM is a high-throughput, memory-efficient inference and serving engine for large language models. The v0.25.0 release introduces Model Runner V2 as the default engine for dense models, removes legacy PagedAttention, and adds extensive support for new models, hardware, and performance optimizations. Key technical advancements include improved support for heterogeneous speculative decoding, a new streaming parser engine, and enhanced support for a wide array of architectures such as GLM-5, MiniMax-M3, and various multimodal models.

key features
  • 01Model Runner V2 as the default engine for dense models
  • 02Universal speculative decoding for heterogeneous vocabularies
  • 03New Streaming Parser Engine for tool-call and reasoning frameworks
  • 04Extensive hardware-specific performance optimizations for NVIDIA Blackwell, AMD ROCm, and Intel XPU
  • 05Removal of legacy PagedAttention in favor of V1/MRv2 backends
  • 06Enhanced quantization support, including NVFP4, FP8 MoE, and Humming weight-only inference