[Core] Move max_concurrent_batches to VllmConfig (#44274)

Signed-off-by: Nick Hill <nickhill123@gmail.com>
This commit is contained in:
Nick Hill
2026-06-02 08:57:25 -07:00
committed by GitHub
parent 774e552397
commit cab5c9a2a9
11 changed files with 25 additions and 37 deletions
-8
View File
@@ -96,14 +96,6 @@ class RayDistributedExecutor(Executor):
self.scheduler_output: SchedulerOutput | None = None
@property
def max_concurrent_batches(self) -> int:
"""Ray distributed executor supports pipeline parallelism,
meaning that it allows PP size batches to be executed concurrently.
"""
pp_size = self.parallel_config.pipeline_parallel_size
return 2 if pp_size <= 1 and self.scheduler_config.async_scheduling else pp_size
def shutdown(self) -> None:
if logger:
# Somehow logger can be None here.