[DP] Internal Load Balancing Per Node [one-pod-per-node] (#21238)
Signed-off-by: Robert Shaw <robshaw@redhat.com> Signed-off-by: Nick Hill <nhill@redhat.com> Signed-off-by: Tyler Michael Smith <tyler@neuralmagic.com> Co-authored-by: Robert Shaw <robshaw@redhat.com> Co-authored-by: Nick Hill <nhill@redhat.com> Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>
This commit is contained in:
co-authored by
Robert Shaw
Nick Hill
Tyler Michael Smith
parent
eec6942014
commit
d5b981f8b1
@@ -565,8 +565,8 @@ def test_engine_core_proc_instantiation_cuda_empty(
|
||||
|
||||
from vllm.v1.engine.utils import EngineZmqAddresses
|
||||
|
||||
def mock_startup_handshake(self, handshake_socket, on_head_node,
|
||||
parallel_config):
|
||||
def mock_startup_handshake(self, handshake_socket, local_client,
|
||||
headless, parallel_config):
|
||||
return EngineZmqAddresses(inputs=["tcp://127.0.0.1:5555"],
|
||||
outputs=["tcp://127.0.0.1:5556"],
|
||||
coordinator_input=None,
|
||||
|
||||
Reference in New Issue
Block a user