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

[Doc] Add engine args back in to the docs (#20674)

Browse Source 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
This commit is contained in:
Harry Mellor
2025-07-10 16:02:40 +01:00
committed by GitHub
parent 77f77a951e
commit 3482fd7e4e
14 changed files with 218 additions and 40 deletions
Download Patch File Download Diff File Expand all files Collapse all files

15
docs/configuration/engine_args.md
View File

@@ -1,3 +1,7 @@
---
toc_depth: 3
---
# Engine Arguments
Engine arguments control the behavior of the vLLM engine.
@@ -5,11 +9,12 @@ Engine arguments control the behavior of the vLLM engine.
- For [offline inference](../serving/offline_inference.md), they are part of the arguments to [LLM][vllm.LLM] class.
- For [online serving](../serving/openai_compatible_server.md), they are part of the arguments to `vllm serve`.
You can look at [EngineArgs][vllm.engine.arg_utils.EngineArgs] and [AsyncEngineArgs][vllm.engine.arg_utils.AsyncEngineArgs] to see the available engine arguments.
The engine argument classes, [EngineArgs][vllm.engine.arg_utils.EngineArgs] and [AsyncEngineArgs][vllm.engine.arg_utils.AsyncEngineArgs], are a combination of the configuration classes defined in [vllm.config][]. Therefore, if you are interested in developer documentation, we recommend looking at these configuration classes as they are the source of truth for types, defaults and docstrings.
However, these classes are a combination of the configuration classes defined in [vllm.config][]. Therefore, we would recommend you read about them there where they are best documented.
## `EngineArgs`
For offline inference you will have access to these configuration classes and for online serving you can cross-reference the configs with `vllm serve --help`, which has its arguments grouped by config.
--8<-- "docs/argparse/engine_args.md"
!!! note
Additional arguments are available to the [AsyncLLMEngine][vllm.engine.async_llm_engine.AsyncLLMEngine] which is used for online serving. These can be found by running `vllm serve --help`
## `AsyncEngineArgs`
--8<-- "docs/argparse/async_engine_args.md"