Update README.md

README.md

@@ -3,4 +3,25 @@ license: apache-2.0
 language:
 - en
 - zh
----
+---
+
+# FastMTP: Accelerating LLM Inference with Enhanced Multi-Token Prediction
+
+<p align="left">
+  <strong>Technical report (coming soon)</strong> ·
+  <a href="https://github.com/Tencent-BAC/FastMTP"><strong>Github</strong></a>
+</p>
+
+
+## Overview
+
+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.
+
+## What's Included
+
+This repository contains the model checkpoints for FastMTP, and the processed compressed vocabulary.
+
+## Links
+
+- Technical report (coming soon)
+- Training & inference code: [GitHub Repository](https://github.com/Tencent-BAC/FastMTP)