Check the topology identities where the layout is written, and build at the published widths (#40340)

2026-09-21 12:22:59 -07:00
parent d5fdab7022
commit 2d0e94e3a3
43 changed files with 843 additions and 261 deletions
@@ -44,6 +44,7 @@ from sglang.srt.distributed.parallel_state import (
    initialize_model_parallel,
    set_torch_symm_mem_all_reduce,
 )
+from sglang.test.test_utils import publish_build_topology
 from sglang.utils import is_in_ci

 IS_CI = is_in_ci()
@@ -188,7 +189,8 @@ if __name__ == "__main__":
        rank=rank,
        local_rank=rank % 8,
    )
-    initialize_model_parallel(tensor_model_parallel_size=world_size)
+    publish_build_topology(world_rank=rank, tp_size=world_size)
+    initialize_model_parallel()
    group = get_tensor_model_parallel_group().device_group
    cpu_group = get_tensor_model_parallel_group().cpu_group
    pynccl_comm = get_tensor_model_parallel_group().pynccl_comm