Skip to content

Commit

Permalink
add todo
Browse files Browse the repository at this point in the history
  • Loading branch information
ZeldaHuang committed Aug 30, 2024
1 parent 2e50225 commit 50505fb
Showing 1 changed file with 1 addition and 1 deletion.
2 changes: 1 addition & 1 deletion llumnix/backends/vllm/scheduler.py
Original file line number Diff line number Diff line change
Expand Up @@ -193,7 +193,7 @@ def _get_instance_info(self) -> InstanceInfo:
instance_info.num_seqs = len(instance_info.running_seq_lens)
if self.running:
instance_info.inference_type = self.running[-1].inference_type
# TODO(ZeldaHuang) adpat chunked-prefill
# TODO(ZeldaHuang) adapt chunked-prefill
instance_info.num_batched_tokens = sum([seq_group.request_len for seq_group in self.running])\
if instance_info.inference_type == RequestInferenceType.PREFILL else len(instance_info.running_seq_lens)
instance_info.finished_request_ids = [seq_group.request_id for seq_group in self.running if seq_group.is_finished()]
Expand Down

0 comments on commit 50505fb

Please sign in to comment.