[V0 Deprecation] Remove async_output_proc, preemption mode, delay factor (#25334)
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
This commit is contained in:
@@ -96,16 +96,6 @@ class CudaPlatformBase(Platform):
|
||||
def get_device_total_memory(cls, device_id: int = 0) -> int:
|
||||
raise NotImplementedError
|
||||
|
||||
@classmethod
|
||||
def is_async_output_supported(cls, enforce_eager: Optional[bool]) -> bool:
|
||||
if enforce_eager and not envs.VLLM_USE_V1:
|
||||
logger.warning(
|
||||
"To see benefits of async output processing, enable CUDA "
|
||||
"graph. Since, enforce-eager is enabled, async output "
|
||||
"processor cannot be used")
|
||||
return False
|
||||
return True
|
||||
|
||||
@classmethod
|
||||
def is_fully_connected(cls, device_ids: list[int]) -> bool:
|
||||
raise NotImplementedError
|
||||
|
||||
Reference in New Issue
Block a user