Open-weight & owned stack · Quantization efficiency

vLLM releases 0.31.0 inference server update

Oct 5, 2026

vLLM released version 0.31.0, a large update containing 717 commits from 307 contributors for inference-server users.

Read the original at freedom.techOpens the publisher's site in a new tab

More in Open-weight & owned stack

Cantina releases open apex-flash-1 security modelOct 5 Anthropic Flags GLM-5.3 Cybersecurity Safeguard GapsOct 5 DeepSeek gains narrow US-China AI performance gapOct 5 Government AI platform relies on foreign modelsOct 5 Ivo open-sources Sage legal AI modelOct 5