From ce38ac070b8623c81642ba7ed15f6fd73d170203 Mon Sep 17 00:00:00 2001
From: arjunkshah21 <arjunkshah21@gmail.com>
Date: Sun, 28 Jun 2026 21:32:50 -0700
Subject: [PATCH] Add SuperCompress to Pre-trained Models and Inference

---
 README.md | 1 +
 1 file changed, 1 insertion(+)

diff --git a/README.md b/README.md
index 34ff193..ab8fece 100644
--- a/README.md
+++ b/README.md
@@ -167,6 +167,7 @@ _Libraries for building AI applications, LLM integrations, and autonomous agents
   - [transformers](https://github.com/huggingface/transformers) - A framework that lets you easily use pre-trained transformer models for NLP, vision, and audio tasks.
   - [unsloth](https://github.com/unslothai/unsloth) - A library for faster LLM fine-tuning and training with reduced memory usage.
   - [vllm](https://github.com/vllm-project/vllm) - A high-throughput and memory-efficient inference and serving engine for LLMs.
+- [SuperCompress](https://supercompress.vercel.app) - Learned prompt compression that reduces LLM token costs by ~65% using a ~5K-param CPU policy (~60ms latency), preserving answer quality. Open-source (MIT).
 - Speech
   - [openai-whisper](https://github.com/openai/whisper) - A general-purpose automatic speech recognition model trained on 680k hours of multilingual and multitask supervised data.
   - [funasr](https://github.com/modelscope/FunASR) - Industrial-grade speech recognition toolkit with 170x realtime speed, 50+ languages, speaker diarization, and emotion detection.