[P/D][KVPool]Mooncake Layerwise Connector supports kv_pool (#7032)
### What this PR does / why we need it?
This PR creates and registers `ascend_multi_connector`, which allows the
`mooncake_layerwise_connector` to use the kv_pooling feature.
We unregister the original vllm's `MultiConnector` and replace it with
`AscendMultiConnector` when registering the connectors.
### Does this PR introduce _any_ user-facing change?
No. User can use `MultiConnector` to initialize `AscendMultiConnector`.
### How was this patch tested?
By CI.
- vLLM version: v0.16.0
- vLLM main:
4034c3d32e
---------
Signed-off-by: nwpu-zxr <zhouxuerong2@huawei.com>
This commit is contained in:
@@ -19,6 +19,13 @@ from vllm.distributed.kv_transfer.kv_connector.factory import KVConnectorFactory
|
||||
|
||||
|
||||
def register_connector():
|
||||
# override multi_connector as ascend_multi_connector
|
||||
if "MultiConnector" in KVConnectorFactory._registry:
|
||||
KVConnectorFactory._registry.pop("MultiConnector")
|
||||
KVConnectorFactory.register_connector(
|
||||
"MultiConnector", "vllm_ascend.distributed.kv_transfer.ascend_multi_connector", "AscendMultiConnector"
|
||||
)
|
||||
|
||||
KVConnectorFactory.register_connector(
|
||||
"MooncakeConnectorV1", "vllm_ascend.distributed.kv_transfer.kv_p2p.mooncake_connector", "MooncakeConnector"
|
||||
)
|
||||
|
||||
Reference in New Issue
Block a user