llm-semantic-router/Vela-1.0-Encoder-307M-Feedback

Add portable FP32 ONNX inference

Add original mmBERT evaluation comparison for Vela Feedback

Simplify Vela quick starts and model cards

Release Vela on the unified Encoder base

Unify Vela model cards with Semantic Router branding

Add Vela Embedding to the model family

Improve long-context AMD inference with qualified exact attention

Release Vela 1.0 Feedback

initial commit