v3.0.1

• Fix invalid max tokens count
• Fix security vulnerabilities flagged by Dependabot
• Add more unit tests
• Add integration tests
• Add code coverage validation in CI

v3.0.1-rc1

• Fix invalid max tokens count
• Add more unit tests
• Add integration tests
• Add code coverage validation in CI

v3.0.0

ci: build everything, create release from all the artifacts

v3.0.0-rc2

ci: build everything, create release from all the artifacts

v3.0.0-rc1

bump paddler to 3.0.0

Paddler API Client

Features

• Add paddler_client - Rust library to connect to Paddler
• Embedding, and inference performance improvements
• Update llama.cpp bindings to the latest version

Fixes

• #140 (Can't load HF-Models with unknown model architecture)
• #138 (Error when calling generate_embedding_batch with 2 or more objects)

OpenAI compatibility improvements

• Thank you @jason-ni for the contribution: #152

OpenAI compatibility improvements

• Thank you @jason-ni for the contribution: #152

v2.1.0

License switch

The license was switched from MIT to Apache-2.0, which is more permissive (has explicit patent grants), so it should be easier to adopt in organizations.

Features

• OpenAI compatibility endpoint:
  • Support for max_completion_tokens parameter in /v1/chat/completions endpoint
  • Support for messages parameter in /v1/chat/completions endpoint
  • Support for stream parameter in /v1/chat/completions endpoint

Documentation: https://paddler.intentee.com/docs/migrating-to-paddler/openai-compatibility/

Full Changelog: v2.0.0...v2.1.0

v2.0.0

What's Changed

Long story short, we rewrote most of the llama-server, made it scalable, and bundled that with Paddler. This means you do not have to deploy llama-server alongside Paddler anymore (the fewer moving parts, the better). :)

We also have a new, vastly improved admin panel, and a lot of other fixes, improvements, and changes.

Full Changelog: v1.2.1-rc1...v2.0.0