vllm v0.34.0
# v0.34.0 **1,061 commits from 412 contributors (120 new).** Thank you! ## TL;DR - **10 new models** (Mistral Large 4, MiniMax-M3.1-Flash, Nemotron-3.5-Transcribe, and more!) - **Extensible KV cache is on by default:** vLLM sizes the KV cache from memory actually free after warmup, so most models get a bigger cache and more throughput. - **Model Runner V1 is gone.** Model Runner V2 is now the only GPU runner. - **Big speedups** on Blackwell and MI355X: up to 1.95× decode (Step5 on GB200), 1.6× throughput (GLM-5.3-Flash), 1.24–1.40× faster long-prompt TTFT (GLM-5.3). - **Upgrade check:** default block size is now 64, ROCm 7.2 images are gone, and is required. See [Before you upgrade](#before-you-upgrade). ## Before you upgrade > [!IMPORTANT] > These changes can break existing setups. | Change | What to do | PR | |---|---|---| | Model Runner V1 removed | Remove ; it now fails at startup. Port V1 logits…
Covered by 1 source
- GGitHub Releases↗5d ago