- Jarno Elonen (Improved performance of length-limited json strings)
- Benedikt Fuchs (Bug fixes)
- Ahmet Erdem from NVIDIA (NVIDIA TensorRT-LLM support)
- Josh C (Bug fixes)
- Brian Dashore (ExLlamaV2 improvements)
- turboderp (ExLlamaV2 improvements)
- Ari Weinstein (JSONSchemaParser performance improvements)
- NJordan72 (JSONSchemaParser Bug Fixes)
- Andrew Wang (JSONSchemaParser exponent parsing and multi eos token support)
The best way to help the library is to look at the open issues and see if there is anything you can help with. If you have an idea for a new feature or a bug fix, please open an issue first to discuss it.
We are always looking to integrate into more inference frameworks. If you have a framework you would like to see supported, please open an issue and let us know.