From f24273dc03d8eadedd681c68ee62a49a889b7deb Mon Sep 17 00:00:00 2001 From: tzhouam Date: Fri, 13 Feb 2026 09:50:11 +0000 Subject: [PATCH] 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 --- .../installation/gpu/cuda.inc.md | 10 +++++----- docs/getting_started/quickstart.md | 4 ++-- ...mpletion_client_for_multimodal_generation.py | 4 ++-- vllm_omni/entrypoints/openai/serving_chat.py | 17 ++++++----------- 4 files changed, 15 insertions(+), 20 deletions(-) diff --git a/docs/getting_started/installation/gpu/cuda.inc.md b/docs/getting_started/installation/gpu/cuda.inc.md index 09323cd25..18348c792 100644 --- a/docs/getting_started/installation/gpu/cuda.inc.md +++ b/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 diff --git a/docs/getting_started/quickstart.md b/docs/getting_started/quickstart.md index c65dd32fb..a3eece127 100644 --- a/docs/getting_started/quickstart.md +++ b/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 diff --git a/examples/online_serving/qwen3_omni/openai_chat_completion_client_for_multimodal_generation.py b/examples/online_serving/qwen3_omni/openai_chat_completion_client_for_multimodal_generation.py index e65e76bf1..a3dbc3aa1 100644 --- a/examples/online_serving/qwen3_omni/openai_chat_completion_client_for_multimodal_generation.py +++ b/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, diff --git a/vllm_omni/entrypoints/openai/serving_chat.py b/vllm_omni/entrypoints/openai/serving_chat.py index f7ae73df3..4271d799e 100644 --- a/vllm_omni/entrypoints/openai/serving_chat.py +++ b/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(