[Feature] Add first-class KV hints request envelope for programmatic KV management (#53423)
Signed-off-by: Karen Chung <karenc@nvidia.com>
This commit is contained in:
@@ -22,6 +22,7 @@ from vllm.tasks import SupportedTask
|
||||
from vllm.v1.engine import EngineCoreRequest
|
||||
from vllm.v1.engine.input_processor import InputProcessor
|
||||
from vllm.v1.fault_tolerance.utils import FaultToleranceRequest, FaultToleranceResult
|
||||
from vllm.v1.kv_hints import KvHintsEnvelope
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from vllm.v1.engine import PauseMode
|
||||
@@ -102,6 +103,7 @@ class EngineClient(ABC):
|
||||
priority: int = 0,
|
||||
data_parallel_rank: int | None = None,
|
||||
session_id: str | None = None,
|
||||
kv_hints: KvHintsEnvelope | None = None,
|
||||
reasoning_ended: bool | None = None,
|
||||
reasoning_parser_kwargs: dict[str, Any] | None = None,
|
||||
) -> AsyncGenerator[RequestOutput, None]:
|
||||
|
||||
Reference in New Issue
Block a user