From 81a90e52776503c6cbdccd30fbe53f61c9179bdf Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Nicol=C3=B2=20Lucchesi?= Date: Thu, 5 Feb 2026 13:20:25 +0100 Subject: [PATCH] [Docs] Add bart-plugin to docs (#33905) Signed-off-by: NickLucche --- docs/design/plugin_system.md | 2 +- docs/models/supported_models.md | 10 ++++++++++ docs/usage/v1_guide.md | 9 ++++++--- 3 files changed, 17 insertions(+), 4 deletions(-) diff --git a/docs/design/plugin_system.md b/docs/design/plugin_system.md index 1bf8aea3c6..f8fb099245 100644 --- a/docs/design/plugin_system.md +++ b/docs/design/plugin_system.md @@ -45,7 +45,7 @@ Every plugin has three parts: ## Types of supported plugins -- **General plugins** (with group name `vllm.general_plugins`): The primary use case for these plugins is to register custom, out-of-the-tree models into vLLM. This is done by calling `ModelRegistry.register_model` to register the model inside the plugin function. +- **General plugins** (with group name `vllm.general_plugins`): The primary use case for these plugins is to register custom, out-of-the-tree models into vLLM. This is done by calling `ModelRegistry.register_model` to register the model inside the plugin function. For an example of an official model plugin, see the [bart-plugin](https://github.com/vllm-project/bart-plugin) which adds support for `BartForConditionalGeneration`. - **Platform plugins** (with group name `vllm.platform_plugins`): The primary use case for these plugins is to register custom, out-of-the-tree platforms into vLLM. The plugin function should return `None` when the platform is not supported in the current environment, or the platform class's fully qualified name when the platform is supported. diff --git a/docs/models/supported_models.md b/docs/models/supported_models.md index e07e17ec50..e69f68feed 100644 --- a/docs/models/supported_models.md +++ b/docs/models/supported_models.md @@ -174,6 +174,16 @@ class MyConfig(PretrainedConfig): - The `list` in the first element of the `tuple` contains the names of the input arguments - The `list` in the last element of the `tuple` contains the names of the variables the layer outputs to in your modeling code +### Plugins + +Some model architectures are supported via vLLM plugins. These plugins extend vLLM's capabilities through the [plugin system](../design/plugin_system.md). + +| Architecture | Models | Plugin Repository | +|--------------|--------|-------------------| +| `BartForConditionalGeneration` | BART | [bart-plugin](https://github.com/vllm-project/bart-plugin) | + +For other model architectures not natively supported, in particular for Encoder-Decoder models, we recommend following a similar pattern by implementing support through the plugin system. + ## Loading a Model ### Hugging Face Hub diff --git a/docs/usage/v1_guide.md b/docs/usage/v1_guide.md index 8506e01b96..96850871d0 100644 --- a/docs/usage/v1_guide.md +++ b/docs/usage/v1_guide.md @@ -134,9 +134,12 @@ Please note that prefix caching is not yet supported for any of the above models #### Encoder-Decoder Models -Whisper is supported. Other models requiring cross-attention between separate -encoder and decoder (e.g., `BartForConditionalGeneration`, -`MllamaForConditionalGeneration`) are no longer supported. +Whisper is supported natively. Other encoder-decoder models are supported via the plugin system: + +- **BART**: `BartForConditionalGeneration` is supported via the official [bart-plugin](https://github.com/vllm-project/bart-plugin). + +For other encoder-decoder models (e.g., `MllamaForConditionalGeneration`), we recommend +following a similar pattern by implementing support through the [plugin system](../design/plugin_system.md). ### Features