vLLM v0.25.0: Model Runner V2 Default, PagedAttention Retired, Transformers Backend Parity

Tools official + media 2 src. ~1 min

vLLM v0.25.0 (July 11) makes Model Runner V2 the default for all dense models and permanently removes the legacy PagedAttention implementation. The HuggingFace Transformers modeling backend now achieves performance parity with native vLLM kernels and gains FP8 MoE support. A new unified Streaming Parser Engine ships for tool-call and reasoning parsing covering Kimi k2.5–k2.7, seed_oss, and DeepSeek V4. Universal speculative decoding gains support for heterogeneous vocabularies. The release aggregates 558 commits from 232 contributors, 64 of them new.

Why it matters

Retiring PagedAttention in favor of Model Runner V2 marks a clean break from vLLM's original architecture; combined with Transformers backend parity, HuggingFace model authors can now serve their models via vLLM with native performance without custom kernels.

Importance: 4/5

Flagship v0.25.0 removes legacy PagedAttention, makes Model Runner V2 default, and brings Transformers backend to performance parity — architectural milestone for open-source LLM serving (558 commits, 232 contributors)

vllm inference open-source serving infrastructure

Sources

official Release v0.25.0 · vllm-project/vllm

media vLLM on X: vLLM v0.25.0 is out!