arxiv

Author: preminstrel

README.md

@@ -112,7 +112,7 @@ If you find ShadowKV useful or relevant to your project and research, please kin
 @article{sun2024shadowkv,
   title={ShadowKV: KV Cache in Shadows for High-Throughput Long-Context LLM Inference},
   author={Sun, Hanshi and Chang, Li-Wen and Bao, Wenlei and Zheng, Size and Zheng, Ningxin and Liu, Xin and Dong, Harry and Chi, Yuejie and Chen, Beidi},
-  journal={arXiv preprint arXiv:2410.XXXXX},
+  journal={arXiv preprint arXiv:2410.21465},
   year={2024}
 }
 ```

index.html

@@ -108,7 +108,7 @@ <h1 class="title is-2 publication-title" style="display: inline;"> ShadowKV: KV
 
                 <!-- ArXiv abstract Link -->
                 <span class="link-block">
-                    <a href="https://arxiv.org/abs/2410.XXXX" target="_blank"
+                    <a href="https://arxiv.org/abs/2410.21465" target="_blank"
                     class="external-link button is-normal is-rounded is-dark">
                     <span class="icon">
                         <i class="ai ai-arxiv"></i>
@@ -280,7 +280,7 @@ <h2 class="title is-3" style="text-align: center"><img src="static/images/Shadow
                 </p>
 
                 <p>
-                In our <a style="color: #209CEE" href="https://arxiv.org/abs/2410.XXXXX target="_blank">paper</a>, we show that ShadowKV can <b>reduce the GPU memory footprint of the KV cache by over 6x without accuracy degradation on a wide range of models and evaluation benchmarks with minimal sparse KV cache budget</b>.
+                In our <a style="color: #209CEE" href="https://arxiv.org/abs/2410.21465 target="_blank">paper</a>, we show that ShadowKV can <b>reduce the GPU memory footprint of the KV cache by over 6x without accuracy degradation on a wide range of models and evaluation benchmarks with minimal sparse KV cache budget</b>.
                 </p>
             </div>
             <div class="figure">
@@ -362,7 +362,7 @@ <h2 class="title">BibTeX</h2>
       <pre><code>@article{sun2024shadowkv,
     title={ShadowKV: KV Cache in Shadows for High-Throughput Long-Context LLM Inference},
     author={Sun, Hanshi and Chang, Li-Wen and Bao, Wenlei and Zheng, Size and Zheng, Ningxin and Liu, Xin and Dong, Harry and Chi, Yuejie and Chen, Beidi},
-    journal={arXiv preprint arXiv:2410.XXXXX},
+    journal={arXiv preprint arXiv:2410.21465},
     year={2024}
 }</code></pre>
     </div>