Releases

Track the latest versions, updates and changelogs for all TensorFoundry products.

Olla v0.0.27
patch

Olla v0.0.27

We've added native support for LMDeploy after so long as well as bugfixes for sticky sessions thanks to @lbatalha.

  • Add aimock test harness for sticky sessions
  • Add language tags to skill code fences
  • Add lmdeploy backend docs
  • Add lmdeploy model converter and wire into factory and routes
View Release Notes
Olla v0.0.26
patch

Olla v0.0.26

This is a bugfix release that addresses SSL connection issues due to mis-handling of the Host header.

  • Lets you build docker image locally without goreleaser
  • Make docker builds portable across arm and amd
View Release Notes
Olla v0.0.25
patch

Olla v0.0.25

Olla is a high-performance proxy and load balancer for LLM infrastructure.

  • Feat: add model alias validation, test coverage, and byte-preserving JSON rewrite
  • Sticky sessions implementation
  • Fix(inspector): copy buffer bytes before pool return to avoid aliasing
  • Fix(inspector): incremental scan with token-level skipping for field-order independence
View Release Notes
Kaizen v0.2.4
beta

Early access preview of Kaizen, TensorFoundry's terminal-first AI coding agent with persistent memory and multi-agent orchestration.

  • Helm orchestrator
  • Scout, Cody & Sage agents
  • Persistent SQLite memory
  • CAS-backed checkpoints
View Release Notes
Olla v0.0.24
patch

olla-v0.0.24

  • Feature: Anthropic agent fixes and improvements
  • Default to Olla proxy engine
  • Fix duplicate increment
  • Fix anthropic tooling bug
View Release Notes
Olla v0.0.23
patch

olla-v0.0.23

  • New Backends: [Docker Model Runner](https://thushan.github.io/olla/integrations/backend/docker-model-runner/) and [vLLM-MLX](https://thushan.github.io/olla/integrations/backend/vllm-mlx/)
  • Support for [Anthropic Passthrough](https://thushan.github.io/olla/concepts/api-translation/?h=passthrough#what-is-passthrough) on supported backends (vllm etc) so we don't translate in Olla
  • Documentation Refinements based on feedback
  • Sensible defaults so you can have a lean config file to overide for most users
View Release Notes
Olla v0.0.22
patch

olla-v0.0.22

  • Fix: ensure model_url is used from endpoint config
  • Chore: december 2025
  • Fix: Alternative method of resolving profile paths
  • Alternative way to join paths for OpenAI compatible profiles
View Release Notes
Olla v0.0.21
patch

olla-v0.0.21

  • Feat: path preservation for routing in Olla
  • Add preserve_path to ep configuration
  • Initial profile consolidation
  • Introduce url_builder to abstract out the target path building
View Release Notes
Olla v0.0.20
patch

olla-v0.0.20

  • Feat: Backend llamacpp
  • Feat: anthropic / message logger (development only)
  • Feat: Anthropic Message format Support
  • Prepare: v0.0.20
View Release Notes
Olla v0.0.19
patch

olla-v0.0.19

  • Feat: backend/sglang
  • Feat: backend/lemonade
  • Fixes: October 2025 performance improvements
  • GetHealthyEndpointsForModel could leak targets that no longer exist.
View Release Notes
Olla v0.0.18
patch

olla-v0.0.18

  • Chore: Consolidate Converters
  • September 2025 updates
  • Refactor: Proxy Configurations
  • September 2025 updates
View Release Notes