From 151e5451c2eb3025ce451ef30556b7087e54c4b1 Mon Sep 17 00:00:00 2001
From: zhanqiuhu <49648934+ZhanqiuHu@users.noreply.github.com>
Date: Sun, 25 Jan 2026 04:20:46 -0500
Subject: [PATCH] [Doc] Add Qwen2.5 models to batch invariance tested models
 (#33016)

Signed-off-by: Zhanqiu Hu <zh338@cornell.edu>
---
 docs/features/batch_invariance.md | 1 +
 1 file changed, 1 insertion(+)

diff --git a/docs/features/batch_invariance.md b/docs/features/batch_invariance.md
index b196db9d9c..0144e2f71f 100644
--- a/docs/features/batch_invariance.md
+++ b/docs/features/batch_invariance.md
@@ -106,6 +106,7 @@ Batch invariance has been tested and verified on the following models:
 - **DeepSeek series**: `deepseek-ai/DeepSeek-V3`, `deepseek-ai/DeepSeek-V3-0324`, `deepseek-ai/DeepSeek-R1`, `deepseek-ai/DeepSeek-V3.1`
 - **Qwen3 (Dense)**: `Qwen/Qwen3-1.7B`, `Qwen/Qwen3-8B`
 - **Qwen3 (MoE)**: `Qwen/Qwen3-30B-A3B`, `Qwen/Qwen3-Next-80B-A3B-Instruct`
+- **Qwen2.5**: `Qwen/Qwen2.5-0.5B-Instruct`, `Qwen/Qwen2.5-1.5B-Instruct`, `Qwen/Qwen2.5-3B-Instruct`, `Qwen/Qwen2.5-7B-Instruct`, `Qwen/Qwen2.5-14B-Instruct`, `Qwen/Qwen2.5-32B-Instruct`
 - **Llama 3**: `meta-llama/Llama-3.1-8B-Instruct`, `meta-llama/Llama-3.2-1B-Instruct`
 
 Other models may also work, but these have been explicitly validated. If you encounter issues with a specific model, please report them on the [GitHub issue tracker](https://github.com/vllm-project/vllm/issues/new/choose).