From d6f4db16565546999f44a71bb8da69c8028c4d44 Mon Sep 17 00:00:00 2001
From: xizhuomengcontin <meng.xizhuo@continuum01.ai>
Date: Sat, 19 Sep 2026 00:18:42 +0800
Subject: [PATCH] Add OrcaReplay to xlite-dev/Awesome-LLM-Inference

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

diff --git a/README.md b/README.md
index 2fe67aa..57c87a3 100644
--- a/README.md
+++ b/README.md
@@ -34,6 +34,7 @@ Awesome-LLM-Inference: A curated list of [📙Awesome LLM Inference Papers with
 ```
 
 ## 🎉Awesome LLM Inference Papers with Codes
+- [Continuum-AI-Corp/OrcaReplay](https://github.com/Continuum-AI-Corp/OrcaReplay) — capture the real LLM request/response stream and replay it offline.
 
 [Awesome LLM Inference for Beginners.pdf](https://github.com/xlite-dev/Awesome-LLM-Inference/releases/download/v0.3/Awesome-LLM-Inference-v0.3.pdf.zip): 500 pages, FastServe, FlashAttention 1/2, FlexGen, FP8, LLM.int8(), PagedAttention, RoPE, SmoothQuant, WINT8/4, Continuous Batching, ZeroQuant 1/2/FP, AWQ etc.