[Doc] Use intersphinx and update entrypoints docs (#5125)
This commit is contained in:
@@ -307,8 +307,6 @@ class AsyncLLMEngine:
|
||||
generate method when there are requests in the waiting queue. The generate
|
||||
method yields the outputs from the :class:`LLMEngine` to the caller.
|
||||
|
||||
NOTE: For the comprehensive list of arguments, see :class:`LLMEngine`.
|
||||
|
||||
Args:
|
||||
worker_use_ray: Whether to use Ray for model workers. Required for
|
||||
distributed execution. Should be the same as
|
||||
|
||||
@@ -70,8 +70,8 @@ class LLMEngine:
|
||||
The :class:`~vllm.LLM` class wraps this class for offline batched inference
|
||||
and the :class:`AsyncLLMEngine` class wraps this class for online serving.
|
||||
|
||||
NOTE: The config arguments are derived from the :class:`~vllm.EngineArgs`
|
||||
class. For the comprehensive list of arguments, see :ref:`engine_args`.
|
||||
The config arguments are derived from :class:`~vllm.EngineArgs`. (See
|
||||
:ref:`engine_args`)
|
||||
|
||||
Args:
|
||||
model_config: The configuration related to the LLM model.
|
||||
|
||||
Reference in New Issue
Block a user