anodyine/vllm-omni
1
0 Fork 0
Code Issues 4 Pull Requests 2 Actions Packages Projects Releases Wiki Activity

[Bugfix] Fix the curl bug of qwen3-omni and doc errors (#135)

Browse Source 
Signed-off-by: Gaohan123 <gaohan19@huawei.com>
This commit is contained in:
Gao Han authored and GitHub committed 2025-12-01 08:01:54 +00:00
1 parent e8fb85d38c
commit d53155f45c
9 files changed
+38 -33
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

docs/.nav.yml
+3 -3
View File
@@ -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/*
docs/api/README.md
+4
View File
@@ -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][]
docs/mkdocs/hooks/generate_examples.py
+3 -2
View File
@@ -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"
docs/user_guide/examples/offline_inference/qwen2_5_omni.md
+6 -6
View File
@@ -1,4 +1,4 @@
# Offline Example of vLLM-Omni for Qwen2.5-omni
# Offline Example of vLLM-Omni for Qwen2.5-Omni
Source <https://github.com/vllm-project/vllm/tree/main/examples/offline_inference/qwen2_5_omni>.
@@ -7,7 +7,7 @@ Source <https://github.com/vllm-project/vllm/tree/main/examples/offline_inferenc
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)
### Multiple Prompts
Download dataset from [seed_tts](https://drive.google.com/file/d/1GlSjVfSHkW3-leKKBlfrjuuTGqQ_xaLP/edit). To get the prompt, you can:
```bash
@@ -48,17 +48,17 @@ sudo apt install ffmpeg
??? abstract "end2end.py"
``````py
--8<-- "/mnt/vllm_open_release/vllm-omni-cursor/vllm-omni/examples/offline_inference/qwen2_5_omni/end2end.py"
--8<-- "examples/offline_inference/qwen2_5_omni/end2end.py"
``````
??? abstract "extract_prompts.py"
``````py
--8<-- "/mnt/vllm_open_release/vllm-omni-cursor/vllm-omni/examples/offline_inference/qwen2_5_omni/extract_prompts.py"
--8<-- "examples/offline_inference/qwen2_5_omni/extract_prompts.py"
``````
??? abstract "run_multiple_prompts.sh"
``````sh
--8<-- "/mnt/vllm_open_release/vllm-omni-cursor/vllm-omni/examples/offline_inference/qwen2_5_omni/run_multiple_prompts.sh"
--8<-- "examples/offline_inference/qwen2_5_omni/run_multiple_prompts.sh"
``````
??? abstract "run_single_prompt.sh"
``````sh
--8<-- "/mnt/vllm_open_release/vllm-omni-cursor/vllm-omni/examples/offline_inference/qwen2_5_omni/run_single_prompt.sh"
--8<-- "examples/offline_inference/qwen2_5_omni/run_single_prompt.sh"
``````
docs/user_guide/examples/offline_inference/qwen3_omni.md
+7 -7
View File
@@ -1,4 +1,4 @@
# Offline Example of vLLM-Omni for Qwen3-omni
# Offline Example of vLLM-Omni for Qwen3-Omni
Source <https://github.com/vllm-project/vllm/tree/main/examples/offline_inference/qwen3_omni>.
@@ -7,9 +7,9 @@ Source <https://github.com/vllm-project/vllm/tree/main/examples/offline_inferenc
Please refer to [README.md](https://github.com/vllm-project/vllm/tree/main/README.md)
## Run examples (Qwen3-omni)
## Run examples (Qwen3-Omni)
### Multiple Prompts
Download dataset from [seed_tts](https://drive.google.com/file/d/1GlSjVfSHkW3-leKKBlfrjuuTGqQ_xaLP/edit). For processing dataset please refer to [Qwen2.5-omni README.md](https://github.com/vllm-project/vllm/tree/main/examples/offline_inference/qwen2_5_omni/README.md)
Download dataset from [seed_tts](https://drive.google.com/file/d/1GlSjVfSHkW3-leKKBlfrjuuTGqQ_xaLP/edit). For processing dataset please refer to [Qwen2.5-Omni README.md](https://github.com/vllm-project/vllm/tree/main/examples/offline_inference/qwen2_5_omni/README.md)
Get into the example folder
```bash
cd examples/offline_inference/qwen3_omni
@@ -44,17 +44,17 @@ sudo apt install ffmpeg
??? abstract "end2end.py"
``````py
--8<-- "/mnt/vllm_open_release/vllm-omni-cursor/vllm-omni/examples/offline_inference/qwen3_omni/end2end.py"
--8<-- "examples/offline_inference/qwen3_omni/end2end.py"
``````
??? abstract "run_multiple_prompts.sh"
``````sh
--8<-- "/mnt/vllm_open_release/vllm-omni-cursor/vllm-omni/examples/offline_inference/qwen3_omni/run_multiple_prompts.sh"
--8<-- "examples/offline_inference/qwen3_omni/run_multiple_prompts.sh"
``````
??? abstract "run_single_prompt.sh"
``````sh
--8<-- "/mnt/vllm_open_release/vllm-omni-cursor/vllm-omni/examples/offline_inference/qwen3_omni/run_single_prompt.sh"
--8<-- "examples/offline_inference/qwen3_omni/run_single_prompt.sh"
``````
??? abstract "run_single_prompt_tp.sh"
``````sh
--8<-- "/mnt/vllm_open_release/vllm-omni-cursor/vllm-omni/examples/offline_inference/qwen3_omni/run_single_prompt_tp.sh"
--8<-- "examples/offline_inference/qwen3_omni/run_single_prompt_tp.sh"
``````
docs/user_guide/examples/offline_inference/qwen_image.md
+2 -2
View File
@@ -49,9 +49,9 @@ Then open `http://localhost:7862/` on your local browser to interact with the we
??? abstract "gradio_demo.py"
``````py
--8<-- "/mnt/vllm_open_release/vllm-omni-cursor/vllm-omni/examples/offline_inference/qwen_image/gradio_demo.py"
--8<-- "examples/offline_inference/qwen_image/gradio_demo.py"
``````
??? abstract "text_to_image.py"
``````py
--8<-- "/mnt/vllm_open_release/vllm-omni-cursor/vllm-omni/examples/offline_inference/qwen_image/text_to_image.py"
--8<-- "examples/offline_inference/qwen_image/text_to_image.py"
``````
docs/user_guide/examples/online_serving/qwen2_5_omni.md
+7 -7
View File
@@ -1,13 +1,13 @@
# Online serving Example of vLLM-Omni for Qwen2.5-omni
# Online serving Example of vLLM-Omni for Qwen2.5-Omni
Source <https://github.com/vllm-project/vllm/tree/main/examples/online_serving/qwen2_5_omni>.
## 🛠️ 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"
``````
docs/user_guide/examples/online_serving/qwen3_omni.md
+5 -5
View File
@@ -5,7 +5,7 @@ Source <https://github.com/vllm-project/vllm/tree/main/examples/online_serving/q
## 🛠️ 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 (Qwen3-Omni)
@@ -21,7 +21,7 @@ vllm serve Qwen/Qwen3-Omni-30B-A3B-Instruct --omni --port 8091 --stage-configs-p
Get into the example folder
```bash
cd examples/online_serving
cd examples/online_serving/qwen3_omni
```
Send request via python
@@ -83,13 +83,13 @@ python gradio_demo.py \
??? abstract "gradio_demo.py"
``````py
--8<-- "/mnt/vllm_open_release/vllm-omni-cursor/vllm-omni/examples/online_serving/qwen3_omni/gradio_demo.py"
--8<-- "examples/online_serving/qwen3_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/qwen3_omni/openai_chat_completion_client_for_multimodal_generation.py"
--8<-- "examples/online_serving/qwen3_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/qwen3_omni/run_curl_multimodal_generation.sh"
--8<-- "examples/online_serving/qwen3_omni/run_curl_multimodal_generation.sh"
``````
examples/online_serving/qwen3_omni/run_curl_multimodal_generation.sh
+1 -1
View File
@@ -41,7 +41,7 @@ code2wav_sampling_params='{
"temperature": 0.0,
"top_p": 1.0,
"top_k": -1,
"max_tokens": 4096 * 16,
"max_tokens": 65536,
"seed": 42,
"detokenize": true,
"repetition_penalty": 1.1