v0.32.0 v2.2.21
vllm-project/vllmOct 18, 2026 → Oct 6, 20260 days between releases
Generating AI comparison
Analyzing what changed between v0.32.0 and v2.2.21. This page updates automatically — usually within a minute.
The Two Releases
v0.32.0
Oct 18, 2026· 4 days ago
This release introduces structured reasoning capabilities via the `/v1/systemone` endpoint and HF parsers, significantly enhances low-precision KV caching (NVFP4, FP8) across hardware, and establishes Model Runner V2 as the default for ROCm. It also brings expanded model support, performance optimizations for startup and serving, and critical security fixes.
Full release notesv2.2.21
Oct 6, 2026· 16 days ago
This release primarily addresses bug fixes within the client-v2 UI editor and notification systems, alongside dependency upgrades for nodemailer, hono, and moment.
Full release notes