[KV Offload] Fix num_tokens_after_batch for different termination types (#49285)

Signed-off-by: Alex <jihuihuang@example.com>
Signed-off-by: Alex <jihui.huang@daocloud.io>
Signed-off-by: Alex <alex.tech.lab@outlook.com>
Signed-off-by: Alex <jihuihuang@users.noreply.github.com>
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: Or Ozeri <oro@il.ibm.com>
This commit is contained in:
AlexHuang
2026-07-26 16:22:58 +03:00
committed by GitHub
co-authored by Claude Or Ozeri
parent 0da6e7f3d6
commit 3f1d40960f
@@ -50,7 +50,7 @@ from vllm.v1.kv_offload.base import (
make_offload_key,
)
from vllm.v1.outputs import KVConnectorOutput
from vllm.v1.request import Request
from vllm.v1.request import Request, RequestStatus
logger = init_logger(__name__)
@@ -976,7 +976,9 @@ class OffloadingConnectorScheduler:
continue
req = req_status.req
if req.is_finished():
if req.status is RequestStatus.FINISHED_ABORTED:
num_tokens_after_batch = req.num_computed_tokens
elif req.is_finished():
num_tokens_after_batch = req.num_tokens
else:
num_scheduled_tokens = scheduler_output.num_scheduled_tokens[req_id]