[Diffusion] Implement paged AR↔DiT KV connector ("v1", reusing vllm's native mooncake) (#6310)
Signed-off-by: asukaqaq-s <1311722138@qq.com> Signed-off-by: Huang, Zeyu <11222265+fhfuih@users.noreply.github.com> Co-authored-by: asukaqaq-s <1311722138@qq.com> Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
This commit is contained in:
18 files changed
+517
-13
No files matched your search
@@ -12,6 +12,8 @@ from vllm_omni.diffusion.diffusion_kv.metadata import DiffusionKVMetadata
|
||||
from vllm_omni.diffusion.request import OmniDiffusionRequest
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from vllm.distributed.kv_transfer.kv_connector.v1.base import KVConnectorMetadata
|
||||
|
||||
from vllm_omni.diffusion.diffusion_kv.request import DiffusionKVRequest
|
||||
|
||||
|
||||
@@ -251,6 +253,9 @@ class DiffusionSchedulerOutput:
|
||||
num_waiting_reqs: int
|
||||
# next request to background-prefetch KV
|
||||
kv_prefetch_job: KVPrefetchJob | None = None
|
||||
# Opaque metadata emitted by a future Scheduler-role connector. PR0 keeps
|
||||
# the input port but does not build or consume it.
|
||||
kv_connector_metadata: KVConnectorMetadata | None = None
|
||||
|
||||
@cached_property
|
||||
def scheduled_request_ids(self) -> list[str]:
|
||||
|
||||
Reference in new issue
Block a user