[V1] [P/D] Refactor KV Connector Path (#21980)

Signed-off-by: David Ben-David <davidb@pliops.com>
Co-authored-by: David Ben-David <davidb@pliops.com>
This commit is contained in:
David Ben-David
2025-08-03 14:03:40 +03:00
committed by GitHub
parent 24d1dffbeb
commit aefeea0fde
12 changed files with 142 additions and 80 deletions

View File

@@ -17,7 +17,7 @@ from vllm.v1.core.kv_cache_manager import KVCacheBlocks
from vllm.v1.core.sched.scheduler import Scheduler
from vllm.v1.kv_cache_interface import (FullAttentionSpec, KVCacheConfig,
KVCacheGroupSpec)
from vllm.v1.outputs import ModelRunnerOutput
from vllm.v1.outputs import KVConnectorOutput, ModelRunnerOutput
from vllm.v1.request import Request
from vllm.v1.structured_output import StructuredOutputManager
@@ -188,8 +188,10 @@ def create_model_runner_output(
logprobs=None,
prompt_logprobs_dict={},
pooler_output=None,
finished_sending=finished_sending,
finished_recving=finished_recving,
kv_connector_output=KVConnectorOutput(
finished_sending=finished_sending,
finished_recving=finished_recving,
),
)