[Misc]: Why not sort the waiting queue before popleft waiting queue?

[zh-jp]

Anything you want to discuss about vllm.

The current logic is to popleft the seq in the waiting queue first, then compare it with the lowest priority seq in the running queue.

vllm/vllm/core/scheduler.py

Lines 988 to 997 in 437f916

	if waiting_queue:
	seq_group = waiting_queue.popleft()
	num_new_seqs = seq_group.get_max_num_running_seqs()
	num_new_tokens_uncached, _ = \
	self._get_num_new_uncached_and_cached_tokens(
	seq_group, SequenceStatus.WAITING, False, budget)
	# Only preempt if priority inversion exists
	while running_queue and self._get_priority(
	running_queue[-1]) > self._get_priority(seq_group):

However, the step of sorting the waiting queue is placed later.

vllm/vllm/core/scheduler.py

Line 1026 in 437f916

waiting_queue = deque(sorted(waiting_queue, key=self._get_priority))

Shouldn't the waiting queue be sorted first then popleft?

Before submitting a new issue...

• Make sure you already searched for relevant issues, and asked the chatbot living at the bottom right corner of the documentation page, which can answer lots of frequently asked questions.

[github-actions]

This issue has been automatically marked as stale because it has not had any activity within 90 days. It will be automatically closed if no further activity occurs within 30 days. Leave a comment if you feel this issue should remain open. Thank you!