v1.7.0 v0.28.0
vllm-project/vllm-omniSep 12, 2026 → Aug 31, 20260 days between releases
Generating AI comparison
Analyzing what changed between v1.7.0 and v0.28.0. This page updates automatically — usually within a minute.
The Two Releases
v1.7.0
Sep 12, 2026· 1 month ago
v1.7.0 is a substantial release featuring a wide array of new public APIs for automation and analytics, alongside architectural refactoring to improve data access patterns. It includes enhancements for inbox reconciliation, WhatsApp native features, and fixes for critical bugs in analytics dashboards and database migrations.
Full release notesv0.28.0
Aug 31, 2026· 2 months ago
This release features 397 merged changes, introducing a new Host Weight Runtime for distributed layerwise offload, a scheduler-managed paged KV cache for diffusion models like HunyuanImage3, and an expanded full-duplex speech stack. It rebases onto vLLM 0.28 and adds extensive support for multimodal models including video, music, and VLA.
Full release notes