diff --git a/docs/api/README.md b/docs/api/README.md index 7c637be4b..4100cc2cd 100644 --- a/docs/api/README.md +++ b/docs/api/README.md @@ -43,9 +43,9 @@ Engine classes for offline and online inference. - [vllm_omni.engine.PromptEmbedsPayload][] - [vllm_omni.engine.arg_utils.AsyncOmniEngineArgs][] - [vllm_omni.engine.arg_utils.OmniEngineArgs][] +- [vllm_omni.engine.input_processor.OmniInputProcessor][] - [vllm_omni.engine.output_processor.MultimodalOutputProcessor][] - [vllm_omni.engine.output_processor.OmniRequestState][] -- [vllm_omni.engine.processor.OmniProcessor][] ## Core @@ -62,13 +62,8 @@ Model execution components. - [vllm_omni.model_executor.models.output_templates.OmniOutput][] - [vllm_omni.model_executor.models.qwen2_5_omni.qwen2_5_omni.Qwen2_5OmniForConditionalGeneration][] - [vllm_omni.model_executor.models.qwen2_5_omni.qwen2_5_omni_talker.Qwen2_5OmniTalkerForConditionalGeneration][] -- [vllm_omni.model_executor.models.qwen2_5_omni.qwen2_5_omni_thinker.Qwen2_5OmniAudioFeatureInputs][] - [vllm_omni.model_executor.models.qwen2_5_omni.qwen2_5_omni_thinker.Qwen2_5OmniConditionalGenerationMixin][] -- [vllm_omni.model_executor.models.qwen2_5_omni.qwen2_5_omni_thinker.Qwen2_5OmniThinkerDummyInputsBuilder][] - [vllm_omni.model_executor.models.qwen2_5_omni.qwen2_5_omni_thinker.Qwen2_5OmniThinkerForConditionalGeneration][] -- [vllm_omni.model_executor.models.qwen2_5_omni.qwen2_5_omni_thinker.Qwen2_5OmniThinkerMultiModalDataParser][] -- [vllm_omni.model_executor.models.qwen2_5_omni.qwen2_5_omni_thinker.Qwen2_5OmniThinkerMultiModalProcessor][] -- [vllm_omni.model_executor.models.qwen2_5_omni.qwen2_5_omni_thinker.Qwen2_5OmniThinkerProcessingInfo][] - [vllm_omni.model_executor.models.qwen2_5_omni.qwen2_5_omni_token2wav.Qwen2_5OmniToken2WavBigVGANModel][] - [vllm_omni.model_executor.models.qwen2_5_omni.qwen2_5_omni_token2wav.Qwen2_5OmniToken2WavDiTModel][] - [vllm_omni.model_executor.models.qwen2_5_omni.qwen2_5_omni_token2wav.Qwen2_5OmniToken2WavForConditionalGenerationVLLM][] @@ -89,9 +84,6 @@ Model execution components. - [vllm_omni.model_executor.models.qwen3_omni.qwen3_omni_moe_thinker.Qwen3OmniMoeThinkerForConditionalGeneration][] - [vllm_omni.model_executor.models.qwen3_omni.qwen3_omni_moe_thinker.Qwen3OmniMoeThinkerMultiModalProcessor][] - [vllm_omni.model_executor.models.qwen3_omni.qwen3_omni_moe_thinker.Qwen3OmniMoeThinkerProcessingInfo][] -- [vllm_omni.model_executor.models.qwen3_omni.qwen3_omni_moe_thinker.Qwen3Omni_VisionTransformer][] -- [vllm_omni.model_executor.models.qwen3_omni.qwen3_omni_moe_thinker.Qwen3_VisionPatchEmbed][] -- [vllm_omni.model_executor.models.qwen3_omni.qwen3_omni_moe_thinker.Qwen3_VisionPatchMerger][] ## Configuration @@ -110,6 +102,7 @@ Worker classes and model runners for distributed inference. - [vllm_omni.diffusion.worker.gpu_worker.WorkerProc][] - [vllm_omni.diffusion.worker.npu.npu_worker.NPUWorker][] - [vllm_omni.diffusion.worker.npu.npu_worker.NPUWorkerProc][] +- [vllm_omni.worker.gpu_ar_model_runner.ExecuteModelState][] - [vllm_omni.worker.gpu_ar_model_runner.GPUARModelRunner][] - [vllm_omni.worker.gpu_ar_worker.GPUARWorker][] - [vllm_omni.worker.gpu_generation_model_runner.GPUGenerationModelRunner][] diff --git a/docs/getting_started/installation/gpu.md b/docs/getting_started/installation/gpu.md index 03758fd93..0f6e4dd84 100644 --- a/docs/getting_started/installation/gpu.md +++ b/docs/getting_started/installation/gpu.md @@ -56,12 +56,6 @@ vLLM-Omni is a Python library that supports the following GPU variants. The libr --8<-- "docs/getting_started/installation/gpu/rocm.inc.md:build-docker" -### Build wheel from source - -=== "AMD ROCm" - - --8<-- "docs/getting_started/installation/gpu/rocm.inc.md:build-wheel-from-source-in-docker" - ### Pre-built images === "NVIDIA CUDA" diff --git a/docs/getting_started/installation/gpu/cuda.inc.md b/docs/getting_started/installation/gpu/cuda.inc.md index e7df09ff4..c88302939 100644 --- a/docs/getting_started/installation/gpu/cuda.inc.md +++ b/docs/getting_started/installation/gpu/cuda.inc.md @@ -18,9 +18,9 @@ Therefore, it is recommended to install vLLM and vLLM-Omni with a **fresh new** #### Installation of vLLM -vLLM-Omni is built based on vLLM v0.12.0. Please install it with command below. +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==0.11.0 --torch-backend=auto ``` #### Installation of vLLM-Omni @@ -89,7 +89,7 @@ docker run --runtime nvidia --gpus 2 \ --env "HF_TOKEN=$HF_TOKEN" \ -p 8091:8091 \ --ipc=host \ - vllm/vllm-omni:v0.12.0rc1 \ + vllm/vllm-omni:v0.11.0rc1 \ --model Qwen/Qwen3-Omni-30B-A3B-Instruct --port 8091 ``` diff --git a/docs/getting_started/installation/gpu/rocm.inc.md b/docs/getting_started/installation/gpu/rocm.inc.md index 887244766..8d9eef4ea 100644 --- a/docs/getting_started/installation/gpu/rocm.inc.md +++ b/docs/getting_started/installation/gpu/rocm.inc.md @@ -15,98 +15,6 @@ vLLM-Omni current recommends the steps in under setup through Docker Images. # --8<-- [end:build-wheel-from-source] -# --8<-- [start:build-wheel-from-source-in-docker] - -#### Get the correct docker environment - -The v0.12.0 releases is on Dec 3, 2025, so we will pull a AMD nightly docker image close to the release period. `rocm/vllm-dev:nightly_main_20251205` is picked as it has a correct `transformers` version that supports qwen3_omni. - -`docker pull rocm/vllm-dev:nightly_main_20251005` - -#### Launch the docker environment - -In this docker environment, we have all the dependencies for vLLM installed, like `flash-attn` and `aiter` - -```bash -#!/bin/bash -docker run -it \ - --privileged \ - --network=host \ - --group-add=video \ - --ipc=host \ - --cap-add=SYS_PTRACE \ - --security-opt seccomp=unconfined \ - --device /dev/kfd \ - --device /dev/dri \ - --name vllmomni \ - rocm/vllm-dev:nightly_main_20251005 \ - bash -``` - -#### Update docker dependencies - -```bash -sudo apt update -sudo apt install ffmpeg -y -``` - -#### Installation of vLLM -Install the v0.12.0 release of vLLM as vLLM-Omni is currently depend on v0.12.0. - -```bash -# uninstall existing vllm which is based on the main branch, not on the releases branch -python3 -m pip uninstall -y vllm -git clone https://github.com/vllm-project/vllm.git vllm0120 -cd vllm0120/ - -# checkout the version tag v0.12.0 -git checkout -b v0.12.0 v0.12.0 - -# you should see 0.12.0 -python -c "import setuptools_scm; print(setuptools_scm.get_version())" - -# PYTORCH_ROCM_ARCH= python3 setup.py develop -PYTORCH_ROCM_ARCH=gfx942 python3 setup.py develop -``` - - -#### Installation of vLLM-Omni - -There are two approaches to installing `vllm-omni` - - -1. Install from PyPI - -```bash -pip install vllm-omni - -# you might want to also download the source code of the same version to run the examples -``` - -2. Install from source - -```bash -# clone and checkout to the release version. -git clone https://github.com/vllm-project/vllm-omni.git -cd vllm-omni -git checkout v0.12.0rc1 -pip install -e . -``` - -#### Setup Environment Variables - -After installing `vllm` and `vllm-omni` please setup the environment variable as well before running any of the examples and command. - -```bash -export MIOPEN_FIND_MODE=FAST -export VLLM_ROCM_USE_AITER=1 -export VLLM_ROCM_USE_AITER_MHA=1 -export VLLM_ROCM_USE_AITER_LINEAR=0 -export VLLM_ROCM_USE_AITER_RMSNORM=0 -``` - -# --8<-- [end:build-wheel-from-source-in-docker] - # --8<-- [start:build-docker] #### Build docker image diff --git a/docs/getting_started/quickstart.md b/docs/getting_started/quickstart.md index e18da6726..8d3fed744 100644 --- a/docs/getting_started/quickstart.md +++ b/docs/getting_started/quickstart.md @@ -12,7 +12,15 @@ This guide will help you quickly get started with vLLM-Omni to perform: ## Installation -Please refer to [installation](installation/README.md) +For installation on GPU using pre-built-wheel: + +```bash +uv venv --python 3.12 --seed +source .venv/bin/activate +uv pip install vllm==0.11.0 --torch-backend=auto +uv pip install vllm-omni +``` +For additional details—including alternative installation methods, installation on NPU and other platforms — please see the installation guide in [installation](installation/README.md) ## Offline Inference diff --git a/docs/user_guide/examples/offline_inference/image_to_image.md b/docs/user_guide/examples/offline_inference/image_to_image.md index 700b2e525..8c03c6323 100644 --- a/docs/user_guide/examples/offline_inference/image_to_image.md +++ b/docs/user_guide/examples/offline_inference/image_to_image.md @@ -16,7 +16,6 @@ python image_edit.py \ --output output_image_edit.png \ --num_inference_steps 50 \ --cfg_scale 4.0 \ - --guidance_scale 1.0 ``` ### Multiple Image Editing (Qwen-Image-Edit-2509) @@ -26,7 +25,7 @@ For multiple image inputs, use `Qwen/Qwen-Image-Edit-2509` or later version: ```bash python image_edit.py \ --model Qwen/Qwen-Image-Edit-2509 \ - --image img1.png img2.png img3.png \ + --image img1.png img2.png \ --prompt "Combine these images into a single scene" \ --output output_image_edit.png \ --num_inference_steps 50 \ diff --git a/docs/user_guide/examples/offline_inference/qwen2_5_omni.md b/docs/user_guide/examples/offline_inference/qwen2_5_omni.md index 0c5a1dc30..7a12e0e14 100644 --- a/docs/user_guide/examples/offline_inference/qwen2_5_omni.md +++ b/docs/user_guide/examples/offline_inference/qwen2_5_omni.md @@ -3,10 +3,6 @@ Source . -## 🛠️ Installation - -Please refer to [README.md](https://github.com/vllm-project/vllm-omni/tree/main/README.md) - ## Run examples (Qwen2.5-Omni) ### Multiple Prompts diff --git a/docs/user_guide/examples/offline_inference/qwen3_omni.md b/docs/user_guide/examples/offline_inference/qwen3_omni.md index e8d98ccb4..e584de5ff 100644 --- a/docs/user_guide/examples/offline_inference/qwen3_omni.md +++ b/docs/user_guide/examples/offline_inference/qwen3_omni.md @@ -3,10 +3,6 @@ Source . -## 🛠️ Installation - -Please refer to [README.md](https://github.com/vllm-project/vllm-omni/tree/main/README.md) - ## Run examples (Qwen3-Omni) ### Multiple Prompts diff --git a/docs/user_guide/examples/online_serving/image_to_image.md b/docs/user_guide/examples/online_serving/image_to_image.md index 3ab1497ff..94d1cec90 100644 --- a/docs/user_guide/examples/online_serving/image_to_image.md +++ b/docs/user_guide/examples/online_serving/image_to_image.md @@ -5,6 +5,8 @@ Source