From df4ec9041f081220a1ca169dd73d4a58933905dd Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Jo=C3=A3o=20Gomes=20Marques?= <32335502+jagmarques@users.noreply.github.com> Date: Thu, 2 Jul 2026 11:40:29 +0200 Subject: [PATCH] update NexusQuant entry: repo moved, refresh numbers --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 2845f6b..8040b2c 100644 --- a/README.md +++ b/README.md @@ -303,7 +303,7 @@ python3 download_pdfs.py # The code is generated by Doubao AI |Date|Title|Paper|Code|Recom| |:---:|:---:|:---:|:---:|:---:| -|2026.03|🔥🔥[**NexusQuant**] NexusQuant: Training-Free KV Cache Compression via E8 Lattice Quantization and Temporal Predictive Coding — 7x compression, -2.26% PPL on Mistral-7B, drop-in one-liner| [[code]](https://github.com/nexusquant/nexusquant)|[[nexusquant]](https://github.com/nexusquant/nexusquant) ![](https://img.shields.io/github/stars/nexusquant/nexusquant.svg?style=social)|⭐️⭐️ | +|2026.03|🔥🔥[**NexusQuant**] NexusQuant: Training-Free KV Cache Compression via E8 Lattice Quantization and Attention-Aware Token Eviction — 6.1x compression, +0.276% PPL on Mistral-7B, drop-in one-liner| [[code]](https://github.com/jagmarques/nexusquant)|[[jagmarques]](https://github.com/jagmarques/nexusquant) ![](https://img.shields.io/github/stars/jagmarques/nexusquant.svg?style=social)|⭐️⭐️ | |2019.11|🔥[MQA] Fast Transformer Decoding: One Write-Head is All You Need(@Google) | [[pdf]](https://arxiv.org/pdf/1911.02150.pdf)|⚠️|⭐️⭐️ | |2022.06|[LTP] Learned Token Pruning for Transformers(@UC Berkeley etc)| [[pdf]](https://arxiv.org/pdf/2107.00910.pdf)|[[LTP]](https://github.com/kssteven418/LTP) ![](https://img.shields.io/github/stars/kssteven418/LTP.svg?style=social)|⭐️ | |2023.05|🔥🔥[**GQA**] GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints(@Google) | [[pdf]](https://arxiv.org/pdf/2305.13245.pdf)|[[flaxformer]](https://github.com/google/flaxformer) ![](https://img.shields.io/github/stars/google/flaxformer.svg?style=social) |⭐️⭐️ |