A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 8, 01:15 UTC
[CI][AMD][BugFix][P/D] Add default_vllm_config to test_moriio_connector.py so tests pass (#33739)
Signed-off-by: Randall Smith <Randall.Smith@amd.com>
rasmith committed
Feb 19, 2026 at 23:32 UTC
0c1dc42748760fc75aef68e973c9ff7a47501337
1 file changed
+8
-5
tests/v1/kv_connector/unit/test_moriio_connector.py
+8
-5
@@ -17,6 +17,7 @@ from vllm.config import (
17
ModelConfig,
18
SchedulerConfig,
19
VllmConfig,
20
+ set_current_vllm_config,
21
)
22
from vllm.distributed.kv_transfer.kv_connector.v1.moriio.moriio_common import (
23
MoRIIOAgentMetadata,
@@ -433,10 +434,11 @@ def test_register_kv_caches(mock_parallel_groups):
434
}
435
)
436
436
- connector = MoRIIOConnector(vllm_config, KVConnectorRole.WORKER)
437
- connector.connector_worker = FakeMorIIOConnectorWorker(
438
- vllm_config, connector.engine_id, hand_shake_latency=0
439
- )
437
+ with set_current_vllm_config(vllm_config):
438
+ connector = MoRIIOConnector(vllm_config, KVConnectorRole.WORKER)
439
+ connector.connector_worker = FakeMorIIOConnectorWorker(
440
+ vllm_config, connector.engine_id, hand_shake_latency=0
441
+ )
442
443
from mori.io import (
444
MemoryDesc,
@@ -523,7 +525,8 @@ def test_moriio_handshake_returns_metadata(mock_parallel_groups):
525
"handshake_port": handshake_port,
526
}
527
)
526
- connector = MoRIIOConnector(vllm_config, KVConnectorRole.WORKER)
528
+ with set_current_vllm_config(vllm_config):
529
+ connector = MoRIIOConnector(vllm_config, KVConnectorRole.WORKER)
530
531
# Execute register_kv_caches
532
connector.register_kv_caches(kv_caches)