From d53155f45c551a07522e2df5ae7ac43db930b450 Mon Sep 17 00:00:00 2001 From: Gao Han Date: Mon, 1 Dec 2025 16:01:54 +0800 Subject: [PATCH] [Bugfix] Fix the curl bug of qwen3-omni and doc errors (#135) Signed-off-by: Gaohan123 --- docs/.nav.yml | 6 +++--- docs/api/README.md | 4 ++++ docs/mkdocs/hooks/generate_examples.py | 5 +++-- .../examples/offline_inference/qwen2_5_omni.md | 12 ++++++------ .../examples/offline_inference/qwen3_omni.md | 14 +++++++------- .../examples/offline_inference/qwen_image.md | 4 ++-- .../examples/online_serving/qwen2_5_omni.md | 14 +++++++------- .../examples/online_serving/qwen3_omni.md | 10 +++++----- .../qwen3_omni/run_curl_multimodal_generation.sh | 2 +- 9 files changed, 38 insertions(+), 33 deletions(-) diff --git a/docs/.nav.yml b/docs/.nav.yml index bc4a00381..aa6470699 100644 --- a/docs/.nav.yml +++ b/docs/.nav.yml @@ -7,11 +7,11 @@ nav: - Examples: - examples/README.md - Offline Inference: - - Offline Example of vLLM-Omni for Qwen2.5-omni: user_guide/examples/offline_inference/qwen2_5_omni.md - - Offline Example of vLLM-Omni for Qwen3-omni: user_guide/examples/offline_inference/qwen3_omni.md + - Offline Example of vLLM-Omni for Qwen2.5-Omni: user_guide/examples/offline_inference/qwen2_5_omni.md + - Offline Example of vLLM-Omni for Qwen3-Omni: user_guide/examples/offline_inference/qwen3_omni.md - Qwen-Image Offline Inference: user_guide/examples/offline_inference/qwen_image.md - Online Serving: - - Online serving Example of vLLM-Omni for Qwen2.5-omni: user_guide/examples/online_serving/qwen2_5_omni.md + - Online serving Example of vLLM-Omni for Qwen2.5-Omni: user_guide/examples/online_serving/qwen2_5_omni.md - Online serving Example of vLLM-Omni for Qwen3-omni: user_guide/examples/online_serving/qwen3_omni.md - General: - usage/* diff --git a/docs/api/README.md b/docs/api/README.md index fcd29d210..bdacb42ef 100644 --- a/docs/api/README.md +++ b/docs/api/README.md @@ -102,6 +102,10 @@ Configuration classes. Worker classes and model runners for distributed inference. +- [vllm_omni.diffusion.worker.gpu_worker.GPUWorker][] +- [vllm_omni.diffusion.worker.gpu_worker.WorkerProc][] +- [vllm_omni.diffusion.worker.npu.npu_worker.NPUWorker][] +- [vllm_omni.diffusion.worker.npu.npu_worker.NPUWorkerProc][] - [vllm_omni.worker.gpu_ar_model_runner.GPUARModelRunner][] - [vllm_omni.worker.gpu_ar_worker.GPUARWorker][] - [vllm_omni.worker.gpu_diffusion_model_runner.GPUDiffusionModelRunner][] diff --git a/docs/mkdocs/hooks/generate_examples.py b/docs/mkdocs/hooks/generate_examples.py index 46bea983f..bccaab6eb 100644 --- a/docs/mkdocs/hooks/generate_examples.py +++ b/docs/mkdocs/hooks/generate_examples.py @@ -192,7 +192,8 @@ class Example: code_fence = "``````" if self.is_code: - content += f'{code_fence}{self.main_file.suffix[1:]}\n--8<-- "{self.main_file}"\n{code_fence}\n' + main_file_rel = self.main_file.relative_to(ROOT_DIR) + content += f'{code_fence}{self.main_file.suffix[1:]}\n--8<-- "{main_file_rel}"\n{code_fence}\n' else: with open(self.main_file) as f: # Skip the title from md snippets as it's been included above @@ -208,7 +209,7 @@ class Example: content += f'??? abstract "{file.relative_to(self.path)}"\n' if file.suffix != ".md": content += f" {code_fence}{file.suffix[1:]}\n" - content += f' --8<-- "{file}"\n' + content += f' --8<-- "{file.relative_to(ROOT_DIR)}"\n' if file.suffix != ".md": content += f" {code_fence}\n" diff --git a/docs/user_guide/examples/offline_inference/qwen2_5_omni.md b/docs/user_guide/examples/offline_inference/qwen2_5_omni.md index 7ec3ed3af..e5effd7f6 100644 --- a/docs/user_guide/examples/offline_inference/qwen2_5_omni.md +++ b/docs/user_guide/examples/offline_inference/qwen2_5_omni.md @@ -1,4 +1,4 @@ -# Offline Example of vLLM-Omni for Qwen2.5-omni +# Offline Example of vLLM-Omni for Qwen2.5-Omni Source . @@ -7,7 +7,7 @@ Source . @@ -7,9 +7,9 @@ Source . ## 🛠️ Installation -Please refer to [README.md](https://github.com/vllm-project/vllm/tree/main/examples/README.md) +Please refer to [README.md](https://github.com/vllm-project/vllm/tree/main/README.md) -## Run examples (Qwen2.5-omni) +## Run examples (Qwen2.5-Omni) Launch the server ```bash @@ -21,7 +21,7 @@ vllm serve Qwen/Qwen2.5-Omni-7B --omni --port 8091 --stage-configs-path /path/to Get into the example folder ```bash -cd examples/online_serving +cd examples/online_serving/qwen2_5_omni ``` Send request via python @@ -79,13 +79,13 @@ python gradio_demo.py \ ??? abstract "gradio_demo.py" ``````py - --8<-- "/mnt/vllm_open_release/vllm-omni-cursor/vllm-omni/examples/online_serving/qwen2_5_omni/gradio_demo.py" + --8<-- "examples/online_serving/qwen2_5_omni/gradio_demo.py" `````` ??? abstract "openai_chat_completion_client_for_multimodal_generation.py" ``````py - --8<-- "/mnt/vllm_open_release/vllm-omni-cursor/vllm-omni/examples/online_serving/qwen2_5_omni/openai_chat_completion_client_for_multimodal_generation.py" + --8<-- "examples/online_serving/qwen2_5_omni/openai_chat_completion_client_for_multimodal_generation.py" `````` ??? abstract "run_curl_multimodal_generation.sh" ``````sh - --8<-- "/mnt/vllm_open_release/vllm-omni-cursor/vllm-omni/examples/online_serving/qwen2_5_omni/run_curl_multimodal_generation.sh" + --8<-- "examples/online_serving/qwen2_5_omni/run_curl_multimodal_generation.sh" `````` diff --git a/docs/user_guide/examples/online_serving/qwen3_omni.md b/docs/user_guide/examples/online_serving/qwen3_omni.md index c593202c2..975ed54da 100644 --- a/docs/user_guide/examples/online_serving/qwen3_omni.md +++ b/docs/user_guide/examples/online_serving/qwen3_omni.md @@ -5,7 +5,7 @@ Source