Implement Async Scheduling (#19970)

Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
This commit is contained in:
Woosuk Kwon
2025-07-14 23:01:46 -07:00
committed by GitHub
parent 85bd6599e4
commit d4d309409f
11 changed files with 508 additions and 148 deletions

View File

@@ -367,6 +367,8 @@ class MultiprocExecutor(Executor):
@property
def max_concurrent_batches(self) -> int:
if self.scheduler_config.async_scheduling:
return 2
return self.parallel_config.pipeline_parallel_size
def _get_output_rank(self) -> int: