From 41ffcd478df9a4acd2ea186669fd81523b6be8d0 Mon Sep 17 00:00:00 2001 From: Srinivas Billa Date: Fri, 24 Jan 2025 22:48:41 +0530 Subject: [PATCH] vllm needs to specifically set multiple image per call --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index ad9b184..169e1b8 100644 --- a/README.md +++ b/README.md @@ -231,7 +231,7 @@ We provide three model sizes on Hugging Face: **2B**, **7B**, and **72B**. To ac Run the command below to start an OpenAI-compatible API service: ```bash -python -m vllm.entrypoints.openai.api_server --served-model-name ui-tars --model +python -m vllm.entrypoints.openai.api_server --served-model-name ui-tars --model --limit-mm-per-prompt "image=10" ``` Then you can use the chat API as below with the gui prompt (choose from mobile or computer) and base64-encoded local images (see [OpenAI API protocol document](https://platform.openai.com/docs/guides/vision/uploading-base-64-encoded-images) for more details), you can also use it in [UI-TARS-desktop](https://github.com/bytedance/UI-TARS-desktop):