[Bugfix][FT] Pass stateless process-group timeouts explicitly (#58611)

Signed-off-by: Tyler Michael Smith <tlrmchlsmth@gmail.com>
Co-authored-by: Codex <noreply@openai.com>
This commit is contained in:
Tyler Michael Smith
2026-09-29 03:14:02 +00:00
committed by GitHub
co-authored by Codex
parent cf971b419a
commit 4406874e7c
6 changed files with 39 additions and 14 deletions
+15
View File
@@ -5,6 +5,7 @@ import json
import logging
import os
from dataclasses import MISSING, Field, asdict, dataclass, field
from datetime import timedelta
from pathlib import Path
from types import SimpleNamespace
from typing import cast
@@ -1464,6 +1465,20 @@ def test_all2all_backend_has_portable_default():
assert ParallelConfig().all2all_backend == "allgather_reducescatter"
def test_dp_group_uses_configured_timeout_without_current_config(monkeypatch):
monkeypatch.setattr(vllm_config_module, "_current_vllm_config", None)
config = ParallelConfig(cpu_distributed_timeout_seconds=30)
with (
patch(
"vllm.distributed.utils.rendezvous",
return_value=iter([(torch.distributed.HashStore(), 0, 1)]),
),
patch("vllm.distributed.utils.init_gloo_process_group") as init_group,
):
config.stateless_init_dp_group()
assert init_group.call_args.kwargs["timeout"] == timedelta(seconds=30)
@pytest.mark.parametrize(
"dp_size, across_dp, expected",
[(1, False, 4), (1, True, 4), (2, False, 4), (2, True, 8)],