fix error for pre-commit

.gitignore

@@ -176,7 +176,6 @@ tests/
 
 # vLLM-omni specific
 # Model files and checkpoints
-models/
 checkpoints/
 *.bin
 *.safetensors

.pre-commit-config.yaml

@@ -1,6 +1,6 @@
 repos:
   - repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v4.3.0
+    rev: v4.6.0
     hooks:
       # list of supported hooks: https://pre-commit.com/hooks.html
       - id: check-yaml
@@ -13,17 +13,17 @@ repos:
         args: ["--markdown-linebreak-ext=md"]
 
   - repo: https://github.com/PyCQA/isort
-    rev: 5.11.5
+    rev: 5.13.2
     hooks:
       - id: isort
 
   - repo: https://github.com/psf/black
-    rev: 23.1.0
+    rev: 24.10.0
     hooks:
       - id: black
 
   - repo: https://github.com/PyCQA/flake8
-    rev: 4.0.1
+    rev: 7.1.1
     hooks:
       - id: flake8
         args: ["--max-line-length=88", "--extend-ignore=E203,W503"]

CONTRIBUTING.md

@@ -0,0 +1,19 @@
+# Contributing to vLLM
+
+## Getting Started
+
+Setup environment with uv
+```bash
+uv venv --python 3.12 --seed
+source .venv/bin/activate
+```
+
+Pre-commit has been linked to git commit. For run checks locally, please install pre-commit:
+```bash
+uv pip install pre-commit
+```
+
+Then run:
+```bash
+pre-commit run --show-diff-on-failure --color=always --all-files
+```

vllm_omni/entrypoints/api_server.py

@@ -116,9 +116,9 @@ async def get_info():
     return {
         "service": "vllm-omni",
         "version": "0.1.0",
-        "num_stages": omni_llm.get_num_stages()
-        if hasattr(omni_llm, "get_num_stages")
-        else 0,
+        "num_stages": (
+            omni_llm.get_num_stages() if hasattr(omni_llm, "get_num_stages") else 0
+        ),
         "stage_configs": [
             {
                 "stage_id": config.stage_id,

vllm_omni/model_executor/models/registry.py

@@ -0,0 +1,54 @@
+from vllm.model_executor.models.registry import (
+    _VLLM_MODELS,
+    _LazyRegisteredModel,
+    _ModelRegistry,
+)
+
+_OMNI_MODELS = {
+    "Qwen2_5OmniForConditionalGeneration": (
+        "qwen2_5_omni",
+        "Qwen2_5OmniForConditionalGeneration",
+    ),
+    "Qwen2_5OmniThinkerModel": (
+        "qwen2_5_omni_thinker",
+        "Qwen2_5OmniThinkerForConditionalGeneration",
+    ),  # noqa: E501
+    "Qwen2_5OmniTalkerModel": (
+        "qwen2_5_omni_talker",
+        "Qwen2_5OmniTalkerForConditionalGeneration",
+    ),  # noqa: E501
+    "Qwen2_5OmniToken2WavModel": (
+        "qwen2_5_omni_token2wav",
+        "Qwen2_5OmniToken2WavForConditionalGenerationVLLM",
+    ),
+    "Qwen2_5OmniToken2WavDiTModel": (
+        "qwen2_5_omni_token2wav",
+        "Qwen2_5OmniToken2WavModel",
+    ),
+    "Qwen2ForCausalLM_old": ("qwen2_old", "Qwen2ForCausalLM"),  # need to discuss
+}
+
+_VLLM_OMNI_MODELS = {
+    **_VLLM_MODELS,
+    **_OMNI_MODELS,
+}
+
+
+OmniModelRegistry = _ModelRegistry(
+    {
+        **{
+            model_arch: _LazyRegisteredModel(
+                module_name=f"vllm.model_executor.models.{mod_relname}",
+                class_name=cls_name,
+            )
+            for model_arch, (mod_relname, cls_name) in _VLLM_MODELS.items()
+        },
+        **{
+            model_arch: _LazyRegisteredModel(
+                module_name=f"vllm_omni.model_executor.models.{mod_relname}",
+                class_name=cls_name,
+            )
+            for model_arch, (mod_relname, cls_name) in _OMNI_MODELS.items()
+        },
+    }
+)