Update README.md

README.md

@@ -17,6 +17,13 @@ language:
 
 FastMTP is a simple yet effective method that enhances Multi-Token Prediction (MTP) for speculative decoding during inference. Our approach fine-tunes a single MTP head with shared weights across multiple causal draft steps, enabling it to capture longer-range dependencies and achieve higher acceptance rates in speculative decoding. By incorporating language-aware vocabulary compression, we further reduce computational overhead during draft generation. Experimental results across diverse benchmarks demonstrate that FastMTP achieves an average of 2.03× speedup over vanilla next token prediction while maintaining lossless output quality. With low training cost and seamless integration into existing inference frameworks, FastMTP offers a practical and rapidly deployable solution for accelerating LLM inference.
 
+<!-- ![Model](./assets/mtp-overview.png){width=50%} -->
+<img src="./assets/mtp-overview.png" width="50%">
+
+Speedup comparison of different methods across subtasks, evaluated on a single A10 GPU:
+
+<img src="./assets/radar_chart.png" width="30%">
+
 ## What's Included
 
 This repository contains the model checkpoints for FastMTP, and the processed compressed vocabulary.