fix: force synchronization between TP workers when update_weights (#6626)

Co-authored-by: dangkai.dk <dangkai.dk@alibaba-inc.com>
2025-06-25 16:35:59 +08:00
parent 3abc30364d
commit bc2e5645c4
1 changed files with 1 additions and 0 deletions
--- a/python/sglang/srt/managers/scheduler.py
+++ b/python/sglang/srt/managers/scheduler.py
@@ -2235,6 +2235,7 @@ class Scheduler(
                assert flash_cache_success, "Cache flush failed after updating weights"
        else:
            logger.error(message)
+        barrier(group=self.tp_cpu_group)
        return UpdateWeightsFromTensorReqOutput(success, message)

    def get_weights_by_name(self, recv_req: GetWeightsByNameReqInput):