tokenspeed-smg-grpc-proto 0.4.14.post20260802
A new release, version 0.4.14.post20260802, of SMG gRPC proto definitions is now available. This update includes support for several popular large language model inference engines like vLLM and TRT-LLM, alongside frameworks such as MLX and TokenSpeed.
Key takeaways
- Updated SMG gRPC proto definitions released
- Supports vLLM, TRT-LLM, MLX, and SGLang
- Enhances interoperability for LLM inference
- Facilitates integration of advanced AI models
Why it matters
This update is crucial for developers integrating various LLM inference engines into their applications. Improved compatibility and support for frameworks like TokenSpeed can lead to more efficient and flexible AI assistant deployments, impacting performance and feature sets.

