inference Releases

This release introduces extensive new features including support for multiple new AI models (Qwen3.8, DeepSeek V4, Ornith-1.5, Kimi-K3, etc.), new audio and image generation models, enhanced router capabilities with token-aware routing and agent-based orchestration, and various UI enhancements.

Aug 30, 2026

This release introduces extensive support for new models across various modalities including LLMs, embeddings, rerankers, audio, video, and image generation. It also adds significant infrastructure improvements like per-replica worker and GPU placement, alongside enhancements to the WebUI and OCR capabilities.

Aug 15, 2026

Version 3.1.0 introduces significant enhancements to the user interface, including SSO/OIDC login support and multi-dashboard monitoring capabilities. It expands model capabilities by adding support for MiniMax-M3 and new speculative decoding features, alongside new image and audio engines. The release also focuses on stability by addressing numerous bug fixes related to worker management, dependency conflicts, and security vulnerabilities.

Jul 31, 2026

Version 3.0.0 introduces a major frontend overhaul by switching the default interface to Next.js and enabling database-backed authentication by default. The release significantly enhances security with new Audit Center and Security Settings pages, while also providing production-ready offline deployment capabilities via Docker Compose. Numerous bug fixes and model updates ensure improved stability and feature support for the inference platform.

Jul 19, 2026

This release focuses on enhancing Card & Attributes management, introducing new process triggers, and improving security and backup functionalities. It includes numerous fixes for markup editors, versioning settings, and UI/UX improvements across the platform.

Jul 5, 2026

This release introduces security controls for remote code execution, new user and API key management UI, and expanded support for models like VibeThinker and Nex-N2. It also enhances monitoring capabilities by splitting Grafana dashboards and unifying worker labels.

Jul 4, 2026

This release adds support for MiniCPM5, MiniCPM-V, and Tencent Hy-MT2 models while improving UI stability and adding new user management features. Core stability improvements include model loading state management and worker registry self-healing.

Jun 19, 2026

This release introduces support for Basque as a new language option and updates the yt-dlp JS dependency to Node.js 22. It also includes minor fixes to enhance the overall stability and performance of the inference platform.

Jun 11, 2026

A major release focusing on security with OIDC/Keycloak SSO, IP/Key banning, and comprehensive audit logging. It also introduces a revamped logging system using JSON format and a new UI with menu reorganization.

Jun 5, 2026

This release enhances monitoring with a Log Center UI integrated with Elasticsearch, adds DeepSeek V4 models, and introduces an advanced authentication system. It also features UI improvements like a collapsible sidebar.

May 23, 2026

A comprehensive feature release focusing on card modeling, process automation, guest management, and document handling, alongside infrastructure improvements.

May 10, 2026

This release focuses on observability through comprehensive Prometheus metrics and Grafana dashboard integration. It also improves system stability with graceful OOM handling, worker auto-recovery, and vLLM compatibility fixes.

May 9, 2026

This release focuses on replica management improvements, new model support including Qwen3.6, MiniMax-M2.7, and glm-5.1, and various bug fixes related to tool parsers and Docker builds.

Apr 25, 2026

A patch release for version 2.6.0 containing minor bug fixes.

Apr 21, 2026

A patch release for version 2.6.0 containing minor bug fixes.

Apr 21, 2026

The minor version 2.6.0 release focused on bug fixes.

Apr 21, 2026

This release focuses on bug fixes, resolving issues related to application customization, controlled document printing, and updating the Slack link.

Apr 14, 2026

This release adds support for Qwen3.5, introduces audio capabilities with Qwen3-TTS, enhances model replica management with auto-reconnection, and adds various model support including gemma-4.

Apr 13, 2026

This release introduces significant updates including Two-Factor Authentication (2FA), enhanced guest access controls, new process functions for data type conversion, and various improvements to the editor, desktop client, and document handling.

Apr 12, 2026

This release introduces OTEL (OpenTelemetry) support, adds GPU load metrics, upgrades base image to 0.17.1 with aarch64 support, and fixes various issues related to qwen3.5 and MLX backend.

Mar 29, 2026