Update vLLM version to 0.16.0 in quickstart and CUDA installation documentation, and adjust parameters in multimodal generation script for improved performance. Refactor request logging in serving_chat.py for better input tracking.

Signed-off-by: tzhouam <tzhouam@connect.ust.hk>

docs/getting_started/installation/gpu/cuda.inc.md

@@ -20,7 +20,7 @@ Therefore, it is recommended to install vLLM and vLLM-Omni with a **fresh new**
 
 vLLM-Omni is built based on vLLM. Please install it with command below.
 ```bash
-uv pip install vllm==0.15.0 --torch-backend=auto
+uv pip install vllm==0.16.0 --torch-backend=auto
 ```
 
 #### Installation of vLLM-Omni
@@ -34,10 +34,10 @@ uv pip install vllm-omni
 # --8<-- [start:build-wheel-from-source]
 
 #### Installation of vLLM
-If you do not need to modify source code of vLLM, you can directly install the stable 0.15.0 release version of the library
+If you do not need to modify source code of vLLM, you can directly install the stable 0.16.0 release version of the library
 
 ```bash
-uv pip install vllm==0.15.0 --torch-backend=auto
+uv pip install vllm==0.16.0 --torch-backend=auto
 ```
 
 The release 0.14.0 of vLLM is based on PyTorch 2.9.0 which requires CUDA 12.9 environment.
@@ -56,11 +56,11 @@ If you want to check, modify or debug with source code of vLLM, install the libr
 ```bash
 git clone https://github.com/vllm-project/vllm.git
 cd vllm
-git checkout v0.15.0
+git checkout v0.16.0
 ```
 Set up environment variables to get pre-built wheels. If there are internet problems, just download the whl file manually. And set `VLLM_PRECOMPILED_WHEEL_LOCATION` as your local absolute path of whl file.
 ```bash
-export VLLM_PRECOMPILED_WHEEL_LOCATION=https://github.com/vllm-project/vllm/releases/download/v0.15.0/vllm-0.15.0-cp38-abi3-manylinux_2_31_x86_64.whl
+export VLLM_PRECOMPILED_WHEEL_LOCATION=https://github.com/vllm-project/vllm/releases/download/v0.16.0/vllm-0.16.0-cp38-abi3-manylinux_2_31_x86_64.whl
 ```
 Install vllm with command below (If you have no existing PyTorch).
 ```bash

docs/getting_started/quickstart.md

@@ -19,10 +19,10 @@ uv venv --python 3.12 --seed
 source .venv/bin/activate
 
 # On CUDA
-uv pip install vllm==0.15.0 --torch-backend=auto
+uv pip install vllm==0.16.0 --torch-backend=auto
 
 # On ROCm
-uv pip install vllm==0.15.0 --extra-index-url https://wheels.vllm.ai/rocm/0.15.0/rocm700
+uv pip install vllm==0.16.0 --extra-index-url https://wheels.vllm.ai/rocm/0.16.0/rocm700
 
 git clone https://github.com/vllm-project/vllm-omni.git
 cd vllm-omni

examples/online_serving/qwen3_omni/openai_chat_completion_client_for_multimodal_generation.py

@@ -337,8 +337,8 @@ def run_multimodal_generation(args, client: OpenAI) -> None:
     thinker_sampling_params = {
         "temperature": 0.2,
         "top_p": 0.9,
-        "top_k": -1,
-        "max_tokens": 1200,
+        "top_k": 1,
+        "max_tokens": 16384,
         "repetition_penalty": 1.05,
         "logit_bias": {},
         "seed": SEED,

vllm_omni/entrypoints/openai/serving_chat.py

@@ -527,18 +527,13 @@ class OmniOpenAIServingChat(OpenAIServingChat, AudioMixin):
         if self.request_logger is None:
             return
         components = self._extract_prompt_components(inputs)
-        prompt = components.text
-        prompt_token_ids = components.token_ids
-        prompt_embeds = components.embeds
-
-        logger.info(
-            "Received request %s: prompt: %r, params_list: %s, prompt_token_ids: %s, prompt_embeds shape: %s, lora_request: %s.",  # noqa: E501
+        self.request_logger.log_inputs(
             request_id,
-            prompt,
-            params_list,
-            prompt_token_ids,
-            prompt_embeds.shape if prompt_embeds is not None else None,
-            lora_request,
+            components.text,
+            components.token_ids,
+            components.embeds,
+            params=params_list,
+            lora_request=lora_request,
         )
 
     async def chat_completion_stream_generator(