From 01e0a8f284576cff5c7962a2261dfa1036b6b57e Mon Sep 17 00:00:00 2001 From: SYLAR <125541396+lishunyang12@users.noreply.github.com> Date: Sun, 8 Feb 2026 20:36:48 +0800 Subject: [PATCH] [Bugfix] Fix Doc link Rrror (#1263) Signed-off-by: lishunyang --- docs/user_guide/examples/offline_inference/text_to_image.md | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/docs/user_guide/examples/offline_inference/text_to_image.md b/docs/user_guide/examples/offline_inference/text_to_image.md index c0dbfd141..2e8739949 100644 --- a/docs/user_guide/examples/offline_inference/text_to_image.md +++ b/docs/user_guide/examples/offline_inference/text_to_image.md @@ -51,7 +51,8 @@ if __name__ == "__main__": For diffusion pipelines, the stage config field `stage_args.[].runtime.max_batch_size` is 1 by default, and the input list is sliced into single-item requests before feeding into the diffusion pipeline. For models that do internally support - batched inputs, you can [modify this configuration](https://github.com/vllm-project/vllm-omni/tree/main/configuration/stage_configs.md) to let the model accept a longer batch of prompts. + batched inputs, you can [modify this configuration](../../../configuration/stage_configs.md + ) to let the model accept a longer batch of prompts. Apart from string prompt, vLLM-Omni also supports dictionary prompts in the same style as vLLM. This is useful for models that support negative prompts.