[Rebase] Rebase to vllm releases/v0.22.0 (#3891)

Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
Signed-off-by: ZhengWG <zwg0606@gmail.com>
Signed-off-by: david6666666 <530634352@qq.com>
Signed-off-by: Yueqian Lin <linyueqian@outlook.com>
Signed-off-by: nainiu258 <cperfect02@163.com>
Signed-off-by: nainiu258 <101917677+nainiu258@users.noreply.github.com>
Signed-off-by: JasonJ2021 <jasonj@zju.edu.cn>
Signed-off-by: Zhou Taichang <tzhouam@connect.ust.hk>
Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>
Co-authored-by: skf <54565339+skf-1999@users.noreply.github.com>
Co-authored-by: Zheng Wengang <zwg0606@gmail.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
Co-authored-by: WeiQing Chen <40507679+david6666666@users.noreply.github.com>
Co-authored-by: SYLAR <125541396+lishunyang12@users.noreply.github.com>
Co-authored-by: Yueqian Lin <linyueqian@outlook.com>
Co-authored-by: nainiu258 <101917677+nainiu258@users.noreply.github.com>
Co-authored-by: Jason <72191212+JasonJ2021@users.noreply.github.com>
Co-authored-by: Yueqian Lin <70319226+linyueqian@users.noreply.github.com>
This commit is contained in:
62 files changed
+998 -354

No files matched your search

@@ -703,6 +703,7 @@ def test_generation_scheduler_calls_cleanup_on_finished(monkeypatch, mocker: Moc
kv_connector_output=None,
cudagraph_stats=None,
req_id_to_index={"req-s1": 0},
routed_experts=None,
routed_experts_dict=None,
)
@@ -789,6 +790,7 @@ def test_ar_scheduler_defers_cleanup_and_queues_save_on_finished(mocker: MockerF
cudagraph_stats=None,
req_id_to_index={"req-ar": 0},
kv_extracted_req_ids=None,
routed_experts=None,
routed_experts_dict=None,
)
@@ -68,13 +68,13 @@ def test_omni_coordinator_pub_coalescing_on_rapid_queue_updates():
sub_ctx = zmq.Context.instance()
sub = sub_ctx.socket(zmq.SUB)
sub.connect(pub_addr)
sub.connect(coordinator.pub_zmq_addr)
sub.setsockopt(zmq.SUBSCRIBE, b"")
time.sleep(0.3) # PUB/SUB slow-joiner
client = OmniCoordClientForStage(
router_addr,
coordinator.router_zmq_addr,
"tcp://stage:coalesce",
"tcp://stage:coalesce-out",
0,
@@ -131,7 +131,7 @@ def test_omni_coordinator_registration_broadcast():
sub_ctx = zmq.Context.instance()
sub = sub_ctx.socket(zmq.SUB)
sub.connect(pub_addr)
sub.connect(coordinator.pub_zmq_addr)
sub.setsockopt(zmq.SUBSCRIBE, b"")
# ZMQ PUB/SUB slow-joiner: allow SUB to connect before clients register.
@@ -139,9 +139,9 @@ def test_omni_coordinator_registration_broadcast():
# Create 3 stage clients; each auto-registers on init.
clients = [
OmniCoordClientForStage(router_addr, "tcp://stage:10001", "tcp://stage:10001-out", 0),
OmniCoordClientForStage(router_addr, "tcp://stage:10002", "tcp://stage:10002-out", 0),
OmniCoordClientForStage(router_addr, "tcp://stage:10003", "tcp://stage:10003-out", 1),
OmniCoordClientForStage(coordinator.router_zmq_addr, "tcp://stage:10001", "tcp://stage:10001-out", 0),
OmniCoordClientForStage(coordinator.router_zmq_addr, "tcp://stage:10002", "tcp://stage:10002-out", 0),
OmniCoordClientForStage(coordinator.router_zmq_addr, "tcp://stage:10003", "tcp://stage:10003-out", 1),
]
msg = _wait_for_replica_list(sub, expected_count=3)
@@ -183,19 +183,19 @@ def test_omni_coordinator_heartbeat_timeout_handling():
sub_ctx = zmq.Context.instance()
sub = sub_ctx.socket(zmq.SUB)
sub.connect(pub_addr)
sub.connect(coordinator.pub_zmq_addr)
sub.setsockopt(zmq.SUBSCRIBE, b"")
time.sleep(0.3)
# A and B: real clients that send heartbeats every 5s.
client_a = OmniCoordClientForStage(router_addr, "tcp://stage:a", "tcp://stage:a-out", 0)
client_b = OmniCoordClientForStage(router_addr, "tcp://stage:b", "tcp://stage:b-out", 0)
client_a = OmniCoordClientForStage(coordinator.router_zmq_addr, "tcp://stage:a", "tcp://stage:a-out", 0)
client_b = OmniCoordClientForStage(coordinator.router_zmq_addr, "tcp://stage:b", "tcp://stage:b-out", 0)
# C: raw DEALER that sends only registration, no heartbeat.
dealer_ctx = zmq.Context.instance()
dealer_c = dealer_ctx.socket(zmq.DEALER)
dealer_c.connect(router_addr)
dealer_c.connect(coordinator.router_zmq_addr)
reg_event = {
"input_addr": "tcp://stage:c",
"output_addr": "tcp://stage:c-out",
@@ -254,12 +254,12 @@ def test_omni_coordinator_replica_shutdown_handling():
sub_ctx = zmq.Context.instance()
sub = sub_ctx.socket(zmq.SUB)
sub.connect(pub_addr)
sub.connect(coordinator.pub_zmq_addr)
sub.setsockopt(zmq.SUBSCRIBE, b"")
time.sleep(0.3) # PUB/SUB slow-joiner
client = OmniCoordClientForStage(router_addr, "tcp://stage:shutdown", "tcp://stage:shutdown-out", 0)
client = OmniCoordClientForStage(coordinator.router_zmq_addr, "tcp://stage:shutdown", "tcp://stage:shutdown-out", 0)
msg = _wait_for_replica_list(sub, expected_count=1)
assert msg is not None