biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[1/N] Elastic EP Milestone 2 (#34861)

Browse Source 
Signed-off-by: Yongji Wu <wuyongji317@gmail.com>
Signed-off-by: Itay Alroy <ialroy@nvidia.com>
Signed-off-by: Tyler Michael Smith <tlrmchlsmth@gmail.com>
Signed-off-by: Ron Tourgeman <rtourgeman@nvidia.com>
Co-authored-by: Yongji Wu <wuyongji317@gmail.com>
Co-authored-by: Tyler Michael Smith <tlrmchlsmth@gmail.com>
Co-authored-by: Ron Tourgeman <rtourgeman@nvidia.com>
This commit is contained in:
Itay Alroy
2026-02-28 06:46:42 +02:00
committed by GitHub
parent 90805ff464
commit dea268336f
53 changed files with 3613 additions and 1016 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
vllm/entrypoints/cli/serve.py
View File

@@ -246,8 +246,12 @@ def run_multi_api_server(args: argparse.Namespace):
api_server_manager: APIServerProcessManager | None = None
from vllm.v1.engine.utils import get_engine_zmq_addresses
addresses = get_engine_zmq_addresses(vllm_config, num_api_servers)
with launch_core_engines(
vllm_config, executor_class, log_stats, num_api_servers
vllm_config, executor_class, log_stats, addresses, num_api_servers
) as (local_engine_manager, coordinator, addresses):
# Construct common args for the APIServerProcessManager up-front.
api_server_manager_kwargs = dict(