From d2a72f380fea867d0a4bd705136ccb30abe20cb4 Mon Sep 17 00:00:00 2001 From: Zhou Taichang Date: Wed, 21 Jan 2026 11:59:02 +0800 Subject: [PATCH] [Doc] Update rebase doc (#878) Signed-off-by: tzhouam --- README.md | 1 - docs/getting_started/installation/gpu/cuda.inc.md | 8 ++++---- docs/getting_started/quickstart.md | 2 +- pyproject.toml | 2 +- 4 files changed, 6 insertions(+), 7 deletions(-) diff --git a/README.md b/README.md index df377293c..c4a71f126 100644 --- a/README.md +++ b/README.md @@ -15,7 +15,6 @@ Easy, fast, and cheap omni-modality model serving for everyone --- *Latest News* 🔥 -- [2026/01] We released [0.14.0rc1](https://github.com/vllm-project/vllm-omni/releases/tag/v0.14.0). - [2026/01] We released [0.12.0rc1](https://github.com/vllm-project/vllm-omni/releases/tag/v0.12.0rc1) - a major RC milestone focused on maturing the diffusion stack, strengthening OpenAI-compatible serving, expanding omni-model coverage, and improving stability across platforms (GPU/NPU/ROCm), please check our latest [design](https://docs.google.com/presentation/d/1qv4qMW1rKAqDREMXiUDLIgqqHQe7TDPj/edit?usp=sharing&ouid=110473603432222024453&rtpof=true&sd=true). - [2025/11] vLLM community officially released [vllm-project/vllm-omni](https://github.com/vllm-project/vllm-omni) in order to support omni-modality models serving. diff --git a/docs/getting_started/installation/gpu/cuda.inc.md b/docs/getting_started/installation/gpu/cuda.inc.md index 8108bb6c8..5331d2d34 100644 --- a/docs/getting_started/installation/gpu/cuda.inc.md +++ b/docs/getting_started/installation/gpu/cuda.inc.md @@ -22,7 +22,7 @@ Note: Pre-built wheels are currently only available for vLLM-Omni 0.11.0rc1 and vLLM-Omni is built based on vLLM. Please install it with command below. ```bash -uv pip install vllm==0.12.0 --torch-backend=auto +uv pip install vllm==0.14.0 --torch-backend=auto ``` #### Installation of vLLM-Omni @@ -36,13 +36,13 @@ 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 0.12.0 release version of the library +If you do not need to modify source code of vLLM, you can directly install the stable 0.14.0 release version of the library ```bash -uv pip install vllm==0.12.0 --torch-backend=auto +uv pip install vllm==0.14.0 --torch-backend=auto ``` -The release 0.12.0 of vLLM is based on PyTorch 2.9.0 which requires CUDA 12.9 environment. +The release 0.14.0 of vLLM is based on PyTorch 2.9.0 which requires CUDA 12.9 environment. #### Installation of vLLM-Omni Since vllm-omni is rapidly evolving, it's recommended to install it from source diff --git a/docs/getting_started/quickstart.md b/docs/getting_started/quickstart.md index 2de64f79a..6e61e91e4 100644 --- a/docs/getting_started/quickstart.md +++ b/docs/getting_started/quickstart.md @@ -17,7 +17,7 @@ For installation on GPU from source: ```bash uv venv --python 3.12 --seed source .venv/bin/activate -uv pip install vllm==0.12.0 --torch-backend=auto +uv pip install vllm==0.14.0 --torch-backend=auto git clone https://github.com/vllm-project/vllm-omni.git cd vllm-omni uv pip install -e . diff --git a/pyproject.toml b/pyproject.toml index 27cdac12d..51d6ce085 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -40,7 +40,7 @@ dependencies = [ "tqdm>=4.66.0", "torchsde>=0.2.6", # Required for Stable Audio scheduler "openai-whisper>=20250625", - # "vllm==0.12.0", # TODO: fix the entrypoints overwrite problem + # "vllm==0.14.0", # TODO: fix the entrypoints overwrite problem ] [project.optional-dependencies]