llm-api Releases

This release adds several new plugins including an API key probe and AWS Bedrock generator, alongside improvements to existing probes and documentation.

Dec 12, 2025

This release introduces a `--scope` option for defining scanning boundaries and an environment variable to control the state file location, providing users with greater configuration flexibility.

Oct 10, 2025

Version 2.12.0 adds significant new features including response size limiting, unique response filtering, and convenience flags for POST requests, alongside improvements to error messaging and shell completion.

Sep 1, 2025

This release introduces Natural Language Search powered by LLMs, dynamic sorting in overrides, and streaming support for conversational AI. It also includes significant performance optimizations, enhanced join capabilities, and new caching and embedding model support.

Jun 30, 2025

This release adds new command-line flags to feroxbuster, enabling raw HTTP request handling, forced recursion, and progress bar limiting.

Sep 15, 2024

This maintenance release improves cookie parsing robustness, adds ARM builds for macOS, and enhances header filtering and scan time estimation.

Jun 16, 2024

This is a plugin-only release for Focalboard v8.0.0 that updates dependencies for the Mattermost server and plugin webapp to their latest versions.

Jun 13, 2024

This release adds support for the AutoAWQ model quantization format and significantly improves Docker deployment flexibility with multiple BLAS backend options. It also cleans up the configuration approach by removing the default config.yaml and providing an example file instead.

Nov 13, 2023

This release updates core dependencies to support newer model formats, specifically upgrading llama-cpp-python to support the GGUF format and updating GPTQ-related libraries for improved model compatibility.

Oct 25, 2023

This February 2023 release introduces property filters and grouping features, along with fixes for schema migrations, CSS issues, and board link handling.

Oct 11, 2023

This April 2023 release focuses on bug fixes, including issues with attachments, card deletion, and board link display, alongside Ubuntu LTS updates and API security improvements.

Oct 11, 2023

Minimal release notes: "Focalboard v7.11.4 is a plugin only patch for the July 2023 release. **Mattermost**: Update to the latest version of "

Sep 26, 2023

This July 2023 release is a bug fix update with no major new features, incorporating changes from previous versions.

Aug 21, 2023

This major release introduces the Huggingface generic model support for running popular HF models, upgrades to run Llama 2, and streamlines Docker images to just two variants. It represents a significant expansion of supported models and improved deployment options.

Jul 23, 2023

This release adds Triton GPU kernel support for improved performance and restructures model directories to prevent configuration conflicts when switching between models.

Jun 16, 2023

This release restructures the model storage layout by placing each model in its own subdirectory, preventing configuration files from being overwritten when switching between different models.

Jun 8, 2023

May 16, 2023

Bug fixes and stability improvements for safetensor models in GPTQ for Llama models.

May 5, 2023

Rebuilt the GPTQ CUDA Docker image using a simpler bullseye-slim base image for improved efficiency.

Apr 25, 2023

Initial release providing support for running Llama-based model inference on GPU using GPTQ-for-llama quantization.

Apr 23, 2023