Skip to content

Fix data parallel perf regression #6183

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 3 commits into from
May 11, 2025
Merged

Fix data parallel perf regression #6183

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
8337b57
Fix data parallel perf
merrymercy May 11, 2025
0a30a63
Fix
merrymercy May 11, 2025
e33d64d
Fix
merrymercy May 11, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
7 changes: 2 additions & 5 deletions .github/workflows/execute-notebook.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,11 +22,6 @@ jobs:
- name: Checkout code
uses: actions/checkout@v4

- name: Set up Python
uses: actions/setup-python@v4
with:
python-version: '3.9'

- name: Install dependencies
run: |
bash scripts/ci_install_dependency.sh
Expand All @@ -35,6 +30,8 @@ jobs:
apt-get install -y pandoc
apt-get update && apt-get install -y parallel retry

ln -sf "$(which python3)" /usr/bin/python

- name: Setup Jupyter Kernel
run: |
python -m ipykernel install --user --name python3 --display-name "Python 3"
Expand Down
4 changes: 2 additions & 2 deletions python/sglang/srt/managers/data_parallel_controller.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,13 +17,13 @@
import multiprocessing as mp
import signal
import threading
import time
from enum import Enum, auto

import psutil
import setproctitle
import zmq

from sglang.srt.disaggregation.utils import DisaggregationMode
from sglang.srt.layers.dp_attention import compute_dp_attention_world_info
from sglang.srt.managers.io_struct import (
TokenizedEmbeddingReqInput,
Expand Down Expand Up @@ -158,7 +158,7 @@ def launch_tensor_parallel_group_thread(
# This thread cannot be closed because otherwise the `kill_itself_when_parent_died`
# function in scheduler.py will kill the scheduler.
while True:
pass
time.sleep(30 * 24 * 3600)

def launch_dp_attention_schedulers(self, server_args, port_args):
self.launch_tensor_parallel_group(server_args, port_args, 0, None)
Expand Down
Loading