louis_lifu
/
vllm
mirror of https://github.com/vllm-project/vllm
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

[BugFix] Fix a bug in counting running sequences (#266)

This commit is contained in:
Woosuk Kwon 2023-06-26 13:09:02 -07:00 committed by GitHub
parent 2cf1a333b6
commit 526df28fb2
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 6 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
vllm/core/scheduler.py
View File

@ -156,7 +156,9 @@ class Scheduler:
# The total number of sequences in the RUNNING state should not
# exceed the maximum number of sequences.
num_new_seqs = seq_group.num_seqs(status=SequenceStatus.SWAPPED)
num_curr_seqs = len(self.running)
num_curr_seqs = sum(
seq_group.num_seqs(status=SequenceStatus.RUNNING)
for seq_group in self.running)
if num_curr_seqs + num_new_seqs > self.scheduler_config.max_num_seqs:
break
@ -198,7 +200,9 @@ class Scheduler:
# The total number of sequences in the RUNNING state should not
# exceed the maximum number of sequences.
num_new_seqs = seq_group.num_seqs(status=SequenceStatus.WAITING)
num_curr_seqs = len(self.running)
num_curr_seqs = sum(
seq_group.num_seqs(status=SequenceStatus.RUNNING)
for seq_group in self.running)
if num_curr_seqs + num_new_seqs > self.scheduler_config.max_num_seqs:
break