From a33bbcedead464cced9d39a0e304d5453808c464 Mon Sep 17 00:00:00 2001 From: Alicia <115451386+congw729@users.noreply.github.com> Date: Mon, 1 Dec 2025 08:05:24 +0800 Subject: [PATCH] [Fix] Resolve comments & update vLLM-Omni name usages. (#122) Signed-off-by: WANG Cong <115451386+congw729@users.noreply.github.com> --- docs/mkdocs/hooks/generate_api_readme.py | 5 ----- examples/online_serving/qwen2_5_omni/README.md | 4 ++-- examples/online_serving/qwen3_omni/README.md | 4 ++-- mkdocs.yml | 1 - tests/__init__.py | 4 ++-- vllm_omni/entrypoints/async_omni.py | 4 ++-- vllm_omni/worker/gpu_generation_model_runner.py | 4 ++-- 7 files changed, 10 insertions(+), 16 deletions(-) diff --git a/docs/mkdocs/hooks/generate_api_readme.py b/docs/mkdocs/hooks/generate_api_readme.py index 535de983b..eb7bbfdbe 100644 --- a/docs/mkdocs/hooks/generate_api_readme.py +++ b/docs/mkdocs/hooks/generate_api_readme.py @@ -188,11 +188,6 @@ def scan_package(package_name: str = "vllm_omni") -> dict[str, list[str]]: # Add classes (filter out internal ones) for class_name in classes: class_short_name = class_name.split(".")[-1] - - # TODO: Implement worker API reference - if "diffusion.worker.gpu_worker" in class_name: - continue - # Skip if it matches internal patterns (unless it's a main model class) if any(pattern in class_short_name for pattern in internal_patterns): # But include main model classes diff --git a/examples/online_serving/qwen2_5_omni/README.md b/examples/online_serving/qwen2_5_omni/README.md index 2673e8fb0..bf99d1bfb 100644 --- a/examples/online_serving/qwen2_5_omni/README.md +++ b/examples/online_serving/qwen2_5_omni/README.md @@ -2,7 +2,7 @@ ## 🛠️ Installation -Please refer to [README.md](../../README.md) +Please refer to [README.md](../../../README.md) ## Run examples (Qwen2.5-Omni) @@ -18,7 +18,7 @@ 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 diff --git a/examples/online_serving/qwen3_omni/README.md b/examples/online_serving/qwen3_omni/README.md index 06edb5471..6f030e493 100644 --- a/examples/online_serving/qwen3_omni/README.md +++ b/examples/online_serving/qwen3_omni/README.md @@ -2,7 +2,7 @@ ## 🛠️ Installation -Please refer to [README.md](../../README.md) +Please refer to [README.md](../../../README.md) ## Run examples (Qwen3-Omni) @@ -18,7 +18,7 @@ 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 diff --git a/mkdocs.yml b/mkdocs.yml index 067e766e8..31ca350fa 100644 --- a/mkdocs.yml +++ b/mkdocs.yml @@ -86,7 +86,6 @@ plugins: api_root_uri: "api" nav_item_prefix: "" # No prefix in navigation tree (clean names) show_full_namespace: false # Show only module name, not full path - on_implicit_namespace_package: skip # Skip implicit namespace packages without warning exclude: - "re:vllm_omni\\._.*" # Internal modules - "vllm_omni.diffusion.models.qwen_image" # avoid importing vllm in mkdocs building diff --git a/tests/__init__.py b/tests/__init__.py index 0a7176f94..bacd68e5d 100644 --- a/tests/__init__.py +++ b/tests/__init__.py @@ -1,6 +1,6 @@ """ -Test suite for vLLM-omni. +Test suite for vLLM-Omni. This package contains unit tests, integration tests, and benchmarks -for vLLM-omni. +for vLLM-Omni. """ diff --git a/vllm_omni/entrypoints/async_omni.py b/vllm_omni/entrypoints/async_omni.py index 4785978f5..040c18876 100644 --- a/vllm_omni/entrypoints/async_omni.py +++ b/vllm_omni/entrypoints/async_omni.py @@ -52,7 +52,7 @@ logger = init_logger(__name__) class AsyncOmni(EngineClient): - """Async entry point for vLLM-omni inference. + """Async entry point for vLLM-Omni inference. This class provides an asynchronous interface for running multi-modal comprehension and generation models. It orchestrates multiple @@ -193,7 +193,7 @@ class AsyncOmni(EngineClient): logger.warning("[Orchestrator] Failed to stop stage worker: %s", e) def __del__(self) -> None: # best-effort - print("[AsyncOmniLLM] __del__ close()", flush=True) + print("[AsyncOmni] __del__ close()", flush=True) raise Exception("test") try: self.close() diff --git a/vllm_omni/worker/gpu_generation_model_runner.py b/vllm_omni/worker/gpu_generation_model_runner.py index d18b7e956..fa5cab9e6 100644 --- a/vllm_omni/worker/gpu_generation_model_runner.py +++ b/vllm_omni/worker/gpu_generation_model_runner.py @@ -1,4 +1,4 @@ -"""Code2Wav GPU Model Runner for vLLM-omni. +"""Code2Wav GPU Model Runner for vLLM-Omni. Handles direct conversion from codec codes to audio waveforms for Qwen3 Omni MoE Code2Wav. This is a non-autoregressive model that doesn't require sampling or logits computation. @@ -37,7 +37,7 @@ logger = logging.getLogger(__name__) class GPUGenerationModelRunner(OmniGPUModelRunner): - """Generation model runner for vLLM-omni (non-autoregressive). + """Generation model runner for vLLM-Omni (non-autoregressive). - Reuses GPUModelRunner preparation, multimodal handling, and TP/PP/DP glue. - Does not compute logits or perform token sampling.