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 13, 10:45 UTC
[Misc] Cleanup Executor interface (#28441)
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
wangxiyuan committed
Nov 12, 2025 at 06:28 UTC
d4902ba56d9b265698fb53f2d956117454945371
1 file changed
-6
vllm/v1/executor/abstract.py
-6
@@ -294,12 +294,6 @@ class Executor(ABC):
294
"""Reset the multi-modal cache in each worker."""
295
self.collective_rpc("reset_mm_cache")
296
297
- def start_profile(self) -> None:
298
- self.collective_rpc("start_profile")
299
-
300
- def stop_profile(self) -> None:
301
- self.collective_rpc("stop_profile")
302
-
297
def sleep(self, level: int = 1):
298
if self.is_sleeping:
299
logger.warning("Executor is already sleeping.")