amd
/

PARD-Qwen2.5-0.5B

@@ -17,6 +17,7 @@ library_name: transformers
 </p>
 ## Introduction
 PARD is a high-performance speculative decoding method that also enables low-cost adaptation of autoregressive draft models into parallel draft models. It offers the following advantages:
@@ -28,6 +29,16 @@ PARD is a high-performance speculative decoding method that also enables low-cos
 - **High Performance**: When integrated into an optimized inference framework called Transformers+ PARD delivers up to a 4.08× speedup, with LLaMA3.1 8B reaches a state-of-the-art 311.5 tokens per second. When integrated into vLLM, PARD delivers up to 3.06× speedup, outperforming other speculative decoding methods in vLLM by 1.51×.
 ## Model Weights
 | Model Series | Model Name                            | Download      |

 </p>
 ## Introduction
 PARD is a high-performance speculative decoding method that also enables low-cost adaptation of autoregressive draft models into parallel draft models. It offers the following advantages:
 - **High Performance**: When integrated into an optimized inference framework called Transformers+ PARD delivers up to a 4.08× speedup, with LLaMA3.1 8B reaches a state-of-the-art 311.5 tokens per second. When integrated into vLLM, PARD delivers up to 3.06× speedup, outperforming other speculative decoding methods in vLLM by 1.51×.
+<p align="center">
+  <figure style="display: inline-block; text-align: center;">
+    <img src="https://cdn-uploads.huggingface.co/production/uploads/630cb01cc169245d78fe76b6/Dh-7wE-l0YAfU9lXWssKf.png" width="100%">
+    <figcaption style="font-style: italic; margin-top: 2px;">
+      AR and AR+ represent baseline auto-regressive generation using Transformers and Transformers+, respectively. VSD denotes vanilla speculative decoding. PARD refers to the proposed method in this work.
+    </figcaption>
+  </figure>
+</p>
 ## Model Weights
 | Model Series | Model Name                            | Download      |