From dc8b28e0aa6d1b4df85a93d3bdcb30280ca31975 Mon Sep 17 00:00:00 2001 From: Alicia <115451386+congw729@users.noreply.github.com> Date: Wed, 11 Feb 2026 06:00:43 +0800 Subject: [PATCH] [Doc] Sync (#1216) Signed-off-by: Alicia <115451386+congw729@users.noreply.github.com> --- .github/PULL_REQUEST_TEMPLATE.md | 2 +- docs/.nav.yml | 8 ++++---- docs/api/README.md | 7 ++----- .../examples/offline_inference/text_to_image.md | 3 +-- docs/user_guide/examples/online_serving/image_to_image.md | 3 +++ 5 files changed, 11 insertions(+), 12 deletions(-) diff --git a/.github/PULL_REQUEST_TEMPLATE.md b/.github/PULL_REQUEST_TEMPLATE.md index ea9b94c93..2466bc71e 100644 --- a/.github/PULL_REQUEST_TEMPLATE.md +++ b/.github/PULL_REQUEST_TEMPLATE.md @@ -14,7 +14,7 @@ PLEASE FILL IN THE PR DESCRIPTION HERE ENSURING ALL CHECKLIST ITEMS (AT THE BOTT - [ ] The purpose of the PR, such as "Fix some issue (link existing issues this PR will resolve)". - [ ] The test plan, such as providing test command. - [ ] The test results, such as pasting the results comparison before and after, or e2e results -- [ ] (Optional) The necessary documentation update, such as updating `supported_models.md` and `examples` for a new model. +- [ ] (Optional) The necessary documentation update, such as updating `supported_models.md` and `examples` for a new model. **Please run `mkdocs serve` to sync the documentation editions to `./docs`.** - [ ] (Optional) Release notes update. If your change is user facing, please update the release notes draft. diff --git a/docs/.nav.yml b/docs/.nav.yml index e0eb6d674..ae4a58f5c 100644 --- a/docs/.nav.yml +++ b/docs/.nav.yml @@ -15,20 +15,20 @@ nav: - BAGEL-7B-MoT: user_guide/examples/offline_inference/bagel.md - Image-To-Image: user_guide/examples/offline_inference/image_to_image.md - Image-To-Video: user_guide/examples/offline_inference/image_to_video.md - - LoRA Inference Examples: user_guide/examples/offline_inference/lora_inference.md + - LoRA Inference(Diffusion): user_guide/examples/offline_inference/lora_inference.md - Qwen2.5-Omni: user_guide/examples/offline_inference/qwen2_5_omni.md - Qwen3-Omni: user_guide/examples/offline_inference/qwen3_omni.md - - Qwen3-TTS Offline Inference: user_guide/examples/offline_inference/qwen3_tts.md + - Qwen3-TTS: user_guide/examples/offline_inference/qwen3_tts.md - Text-To-Audio: user_guide/examples/offline_inference/text_to_audio.md - Text-To-Image: user_guide/examples/offline_inference/text_to_image.md - Text-To-Video: user_guide/examples/offline_inference/text_to_video.md - Online Serving: - BAGEL-7B-MoT: user_guide/examples/online_serving/bagel.md - Image-To-Image: user_guide/examples/online_serving/image_to_image.md - - Online LoRA Inference (Diffusion): user_guide/examples/online_serving/lora_inference.md + - LoRA Inference(Diffusion): user_guide/examples/online_serving/lora_inference.md - Qwen2.5-Omni: user_guide/examples/online_serving/qwen2_5_omni.md - Qwen3-Omni: user_guide/examples/online_serving/qwen3_omni.md - - Qwen3-TTS Online Serving: user_guide/examples/online_serving/qwen3_tts.md + - Qwen3-TTS: user_guide/examples/online_serving/qwen3_tts.md - Text-To-Image: user_guide/examples/online_serving/text_to_image.md - General: - usage/* diff --git a/docs/api/README.md b/docs/api/README.md index eb3a40950..b4ec398f2 100644 --- a/docs/api/README.md +++ b/docs/api/README.md @@ -104,15 +104,12 @@ Worker classes and model runners for distributed inference. - [vllm_omni.platforms.xpu.worker.xpu_ar_worker.XPUARWorker][] - [vllm_omni.platforms.xpu.worker.xpu_generation_model_runner.XPUGenerationModelRunner][] - [vllm_omni.platforms.xpu.worker.xpu_generation_worker.XPUGenerationWorker][] +- [vllm_omni.worker.base.OmniGPUWorkerBase][] - [vllm_omni.worker.gpu_ar_model_runner.ExecuteModelState][] - [vllm_omni.worker.gpu_ar_model_runner.GPUARModelRunner][] - [vllm_omni.worker.gpu_ar_worker.GPUARWorker][] - [vllm_omni.worker.gpu_generation_model_runner.GPUGenerationModelRunner][] - [vllm_omni.worker.gpu_generation_worker.GPUGenerationWorker][] +- [vllm_omni.worker.gpu_memory_utils.parse_cuda_visible_devices][] - [vllm_omni.worker.gpu_model_runner.OmniGPUModelRunner][] - [vllm_omni.worker.mixins.OmniWorkerMixin][] - - -## Metrics - -- [vllm_omni.metrics.OrchestratorAggregator][] 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 2e8739949..c0dbfd141 100644 --- a/docs/user_guide/examples/offline_inference/text_to_image.md +++ b/docs/user_guide/examples/offline_inference/text_to_image.md @@ -51,8 +51,7 @@ 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](../../../configuration/stage_configs.md - ) to let the model accept a longer batch of prompts. + 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. 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. diff --git a/docs/user_guide/examples/online_serving/image_to_image.md b/docs/user_guide/examples/online_serving/image_to_image.md index b89f0fe82..6be2a4a7e 100644 --- a/docs/user_guide/examples/online_serving/image_to_image.md +++ b/docs/user_guide/examples/online_serving/image_to_image.md @@ -15,6 +15,9 @@ For **multi-image** input editing, use **Qwen-Image-Edit-2509** (QwenImageEditPl vllm serve Qwen/Qwen-Image-Edit --omni --port 8092 ``` +!!! note + If you encounter Out-of-Memory (OOM) issues or have limited GPU memory, you can enable VAE slicing and tiling to reduce memory usage, --vae-use-slicing --vae-use-tiling + ### Multi-Image Edit (Qwen-Image-Edit-2509) ```bash