[Core][Hybrid allocator + connector] Support hybrid allocator + kv cache connector (#30166)
Signed-off-by: Yifan Qiao <yifanqiao@berkeley.edu> Co-authored-by: KuntaiDu <kuntai@uchicago.edu>
This commit is contained in:
@@ -624,7 +624,7 @@ class Worker(WorkerBase):
|
||||
output = self.model_runner.execute_model(
|
||||
scheduler_output, intermediate_tensors
|
||||
)
|
||||
if isinstance(output, (ModelRunnerOutput, NoneType)):
|
||||
if isinstance(output, ModelRunnerOutput | NoneType):
|
||||
return output
|
||||
|
||||
assert isinstance(output, IntermediateTensors)
|
||||
|
||||
Reference in New Issue
Block a user