[improve] made timeout configurable (#3803)

This commit is contained in:
Shenggui Li
2025-02-25 16:26:08 +08:00
committed by GitHub
parent 7036d6fc67
commit c0bb9eb3b3
5 changed files with 26 additions and 1 deletions

View File

@@ -259,6 +259,7 @@ class ModelRunner:
rank=self.tp_rank,
local_rank=self.gpu_id,
distributed_init_method=dist_init_method,
timeout=self.server_args.dist_timeout,
)
initialize_model_parallel(tensor_model_parallel_size=self.tp_size)
initialize_dp_attention(