A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 14, 05:30 UTC
[Docs] Fix griffe warning in base_static_graph.py (#25018)
Signed-off-by: windsonsea <haifeng.yao@daocloud.io>
Michael Yao committed
Sep 17, 2025 at 16:49 UTC
0fb2551c238c7ccbcf6f25ef4646ce6c92f684d1
1 file changed
+8
-3
vllm/compilation/base_static_graph.py
+8
-3
@@ -12,8 +12,13 @@ class AbstractStaticGraphWrapper(Protocol):
12
to be captured as a static graph.
13
"""
14
15
- def __init__(self, runnable: Callable, vllm_config: VllmConfig,
16
- runtime_mode: CUDAGraphMode, **kwargs):
15
+ def __init__(
16
+ self,
17
+ runnable: Callable[..., Any],
18
+ vllm_config: VllmConfig,
19
+ runtime_mode: CUDAGraphMode,
20
+ **kwargs: Any,
21
+ ) -> None:
22
"""
23
Initializes the StaticGraphWrapper class with graph capturing and
24
execution-related configurations.
@@ -31,7 +36,7 @@ class AbstractStaticGraphWrapper(Protocol):
36
"""
37
raise NotImplementedError
38
34
- def __call__(self, *args, **kwargs) -> Any:
39
+ def __call__(self, *args: Any, **kwargs: Any) -> Any:
40
"""
41
Executes the wrapped callable.
42