biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Doc] Add the start of an arch overview page (#10368)

Browse Source
This commit is contained in:
Russell Bryant
2024-11-19 04:52:11 -05:00
committed by GitHub
parent 382b6a4852
commit 5390d6664f
10 changed files with 334 additions and 78 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
docs/source/design/plugin_system.rst
View File

@@ -8,7 +8,7 @@ The community frequently requests the ability to extend vLLM with custom feature
How Plugins Work in vLLM
------------------------
Plugins are user-registered code that vLLM executes. Given vLLM's architecture (see :ref:`class_hierarchy`), multiple processes may be involved, especially when using distributed inference with various parallelism techniques. To enable plugins successfully, every process created by vLLM needs to load the plugin. This is done by the `load_general_plugins <https://github.com/vllm-project/vllm/blob/c76ac49d266e27aa3fea84ef2df1f813d24c91c7/vllm/plugins/__init__.py#L16>`__ function in the ``vllm.plugins`` module. This function is called for every process created by vLLM before it starts any work.
Plugins are user-registered code that vLLM executes. Given vLLM's architecture (see :ref:`arch_overview`), multiple processes may be involved, especially when using distributed inference with various parallelism techniques. To enable plugins successfully, every process created by vLLM needs to load the plugin. This is done by the `load_general_plugins <https://github.com/vllm-project/vllm/blob/c76ac49d266e27aa3fea84ef2df1f813d24c91c7/vllm/plugins/__init__.py#L16>`__ function in the ``vllm.plugins`` module. This function is called for every process created by vLLM before it starts any work.
How vLLM Discovers Plugins
--------------------------
@@ -59,4 +59,4 @@ Guidelines for Writing Plugins
Compatibility Guarantee
-----------------------
vLLM guarantees the interface of documented plugins, such as ``ModelRegistry.register_model``, will always be available for plugins to register models. However, it is the responsibility of plugin developers to ensure their plugins are compatible with the version of vLLM they are targeting. For example, ``"vllm_add_dummy_model.my_llava:MyLlava"`` should be compatible with the version of vLLM that the plugin targets. The interface for the model may change during vLLM's development.
vLLM guarantees the interface of documented plugins, such as ``ModelRegistry.register_model``, will always be available for plugins to register models. However, it is the responsibility of plugin developers to ensure their plugins are compatible with the version of vLLM they are targeting. For example, ``"vllm_add_dummy_model.my_llava:MyLlava"`` should be compatible with the version of vLLM that the plugin targets. The interface for the model may change during vLLM's development.