Release Notes

note

Support is generally provided for both torch.function_name and Tensor.function_name syntaxes. If you find a case where only one is supported, please report it to support@clika.io.

Version 25.12.0 - December 2025

• Major improvements to data handling
• Major bug fixes
• More supported operations
• TensorRT-LLM (NVIDIA) support
• Early QAIRT (Qualcomm) support
• Graph Optimization improvements
• Improved Quantization results
• Early ONNX support