Release v0.4.1

Added

• support for Qwen3 models.
• better dependency management and setup configuration.
• model evaluation method.
• support for MOE model architectures.

Release v0.4.0

Updated

• improved fastapi-server.
• improved bge embedding model serving method.

Release v0.3.8

Updated

• fixed some issues in fastapi-server and langchain pipeline.

Release v0.3.7

Updated

• synchronized with mlx==0.23.0 and mlx-lm==0.21.4

Release v0.3.6

Updated

• created async_generate_step in fast-api
• added token usage information in fast-api
• extended libra router types

Release v0.3.5

Updated

• improved fastAPI server
• support libra confidence router

Release v0.3.4

Updated

• improved the hidden states generation method
• project structure refactoring

Release v0.3.3

Added

• langchain integration
• local_rag and graph_rag example

Updated

• generate method to support hidden states output

Release v0.3.2

Added

• model management, FastAPI-server
• unit test

Updated

• synchronized with the mlx-lm
• simplified README

Release v0.3.1

Updated

• updated mlx_fastchat_worker for supporting mlx >= 0.14.
• updated conda config.