docs: class migration from sphinx to mkdocs (entrypoints)

Signed-off-by: Zerohertz <[email protected]>

Author: Zerohertz

vllm/entrypoints/llm.py

@@ -129,8 +129,7 @@ class LLM:
         compilation_config: Either an integer or a dictionary. If it is an
             integer, it is used as the level of compilation optimization. If it
             is a dictionary, it can specify the full compilation configuration.
-        **kwargs: Arguments for [EngineArgs][vllm.EngineArgs]. (See
-            [engine-args][])
+        **kwargs: Arguments for [`EngineArgs`][vllm.EngineArgs].
 
     Note:
         This class is intended to be used for offline inference. For online
@@ -494,7 +493,8 @@ def collective_rpc(self,
                 `self` argument, in addition to the arguments passed in `args`
                 and `kwargs`. The `self` argument will be the worker object.
             timeout: Maximum time in seconds to wait for execution. Raises a
-                {exc}`TimeoutError` on timeout. `None` means wait indefinitely.
+                [`TimeoutError`][TimeoutError] on timeout. `None` means wait
+                indefinitely.
             args: Positional arguments to pass to the worker method.
             kwargs: Keyword arguments to pass to the worker method.
 

vllm/entrypoints/openai/serving_engine.py

@@ -582,7 +582,8 @@ def _tokenize_prompt_input(
         add_special_tokens: bool = True,
     ) -> TextTokensPrompt:
         """
-        A simpler implementation of {meth}`_tokenize_prompt_input_or_inputs`
+        A simpler implementation of
+        [`_tokenize_prompt_input_or_inputs`][vllm.entrypoints.openai.serving_engine.OpenAIServing._tokenize_prompt_input_or_inputs]
         that assumes single input.
         """
         return next(
@@ -603,7 +604,8 @@ def _tokenize_prompt_inputs(
         add_special_tokens: bool = True,
     ) -> Iterator[TextTokensPrompt]:
         """
-        A simpler implementation of {meth}`_tokenize_prompt_input_or_inputs`
+        A simpler implementation of
+        [`_tokenize_prompt_input_or_inputs`][vllm.entrypoints.openai.serving_engine.OpenAIServing._tokenize_prompt_input_or_inputs]
         that assumes multiple inputs.
         """
         for text in prompt_inputs: