aibrix Releases
57 releases of vllm-project/aibrix
- v0.4.0
Major release introducing Prefill/Decode disaggregation with StormService and RoleSet CRDs, KVCache V1 connector optimizations, KV event synchronization system, and multi-engine deployment support.
Aug 5, 2025
- V0.9.0
This is a massive release featuring 79k lines of code changes, focusing on Gemini 2.5 Pro/Flash integration. It introduces strong static typing, new database implementations, and enhanced image support for autonomous agents.
Jun 9, 2025
- v0.3.0
Major release introducing the AIBrix KVCache Offloading Framework with multi-tier architecture, advanced routing algorithms including Preble and fairness-oriented VTC routing, and comprehensive OpenAI-compatible API support.
May 21, 2025
- v0.2.1
A maintenance release focused on integrating bug fixes and CI improvements from the main branch into the release branch to ensure stability.
Mar 9, 2025
- v0.8.0
This release expands model support by adding Sonnet 3.7 and Perplexity Deep Research, introduces a 'Thinking' option for text generation, and updates the DeepSeek R1 implementation with service fallbacks.
Feb 26, 2025
- v0.2.0
A major feature release introducing distributed inference capabilities, heterogeneous GPU support, and advanced autoscaling strategies to optimize resource utilization.
Feb 19, 2025
- v0.1.2
A minor maintenance release incorporating specific fixes related to LoRA adapter paths and streaming capabilities.
Jan 9, 2025
- v0.1.1
A quick bug fix release addressing timing and configuration issues in the autoscaling components to improve system reliability.
Nov 21, 2024
- v0.1.0
The initial release of AIBrix, establishing the core Kubernetes-based infrastructure for AI inference, including dynamic LoRa management and autoscaling.
Nov 12, 2024
- webapp.2024.5
Minimal release notes: "+ Key transparent image in webapp + Stop inverting black/white for binary images"
Jun 5, 2024
- 0.0.3
May 21, 2024
- 0.6.4
Apr 20, 2024
- 0.0.20.0.2 Release
Minimal release notes: "- Separate logic between 3 main components: Crawler, Parser, Scraper - Add cache layer to CLI app - Add docs - Update"
Apr 17, 2024
- 0.0.1
Mar 16, 2024
- 0.6.1
This release addresses a geometric bug regarding parallel lines and introduces an official Python binding for the library.
Sep 23, 2023
- 0.6.0
Minimal release notes: "Nothing is new. Other than a new set of compiled binaries."
Sep 17, 2023
- 0.5.0
The release focuses on code stability and documentation, fixing deprecation warnings, typos, and improving CLI alpha channel handling.
Oct 9, 2022