v1.5.1 release/0.22.2
roboflow/inferenceAug 28, 2026 → Aug 28, 20260 days between releases
Generating AI comparison
Analyzing what changed between v1.5.1 and release/0.22.2. This page updates automatically — usually within a minute.
The Two Releases
v1.5.1
Aug 28, 2026· 2 months ago
This release introduces an optional S3-compatible shared cache for model files to reduce cold-start latency, adds token-usage outputs for remote VLM Workflow blocks, and ships an experimental CUDA 13 server build. It also includes telemetry for the GStreamer CUDA video producer and fixes several critical issues regarding Modal boundary serialization, workflow worker context, MQTT sink lifecycle, and TRT CUDA-graph capture.
Full release notesrelease/0.22.2
Aug 28, 2026· 2 months ago
Improves workspace management and branch operations with new TUI features while resolving numerous sync, conflict, and PR loading issues.
Full release notes