[Docs] Fix warnings in mkdocs build (#23649)

Signed-off-by: Zerohertz <ohg3417@gmail.com>
Signed-off-by: Hyogeun Oh (오효근) <ohg3417@gmail.com>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
This commit is contained in:
Hyogeun Oh (오효근)
2025-08-26 18:19:23 +00:00
committed by GitHub
co-authored by Harry Mellor
parent 9b0187003e
commit 730d0ac8b9
14 changed files with 66 additions and 58 deletions
+2 -2
View File
@@ -486,10 +486,10 @@ class AsyncLLMEngine(EngineClient):
_engine_class: Type[_AsyncLLMEngine] = _AsyncLLMEngine
def __init__(self,
*args,
*args: Any,
log_requests: bool = True,
start_engine_loop: bool = True,
**kwargs) -> None:
**kwargs: Any) -> None:
if envs.VLLM_USE_V1:
raise ValueError(
"Using V0 AsyncLLMEngine, but envs.VLLM_USE_V1=True. "
+4 -4
View File
@@ -644,10 +644,10 @@ class LLMEngine:
Details:
- Set arrival_time to the current time if it is None.
- Set prompt_token_ids to the encoded prompt if it is None.
- Create `n` number of [Sequence][vllm.Sequence] objects.
- Create a [SequenceGroup][vllm.SequenceGroup] object
from the list of [Sequence][vllm.Sequence].
- Add the [SequenceGroup][vllm.SequenceGroup] object to the
- Create `n` number of [Sequence][vllm.sequence.Sequence] objects.
- Create a [SequenceGroup][vllm.sequence.SequenceGroup] object
from the list of [Sequence][vllm.sequence.Sequence].
- Add the [SequenceGroup][vllm.sequence.SequenceGroup] object to the
scheduler.
Example: