Skip to content

[rollout] feat: add enable_sleep_mode=false update to use expandable_segments when in RolloutMode.STANDALONE #4524

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

Closed
chenjiaoAngel wants to merge 4 commits into from
Closed

[rollout] feat: add enable_sleep_mode=false update to use expandable_segments when in RolloutMode.STANDALONE #4524

Changes from 1 commit
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
1a0ccf6
feat: add enable_sleep_mode update when in RolloutMode.STANDALONE
chenjiaoAngel Dec 15, 2025
c4c9353
fix: fix not import set_expandable_segments
chenjiaoAngel Dec 15, 2025
a9b0168
Merge branch 'main' into sleep_up
chenjiaoAngel Dec 15, 2025
eedc056
fix: fix format according to mr ci
chenjiaoAngel Dec 16, 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
8 changes: 7 additions & 1 deletion verl/workers/rollout/vllm_rollout/vllm_async_server.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -216,6 +216,12 @@ async def launch_server(self, master_address: str = None, master_port: int = Non
)
logger.info(f"override_generation_config: {override_generation_config}")

enable_sleep_mode = True
if self.rollout_mode == RolloutMode.STANDALONE:
enable_sleep_mode = False
logger.info(f"enable_sleep_mode: {enable_sleep_mode}, set_expandable_segments is True")
set_expandable_segments(True)

args = {
"dtype": self.config.dtype,
"load_format": self.config.load_format,
Expand All @@ -226,7 +232,7 @@ async def launch_server(self, master_address: str = None, master_port: int = Non
"enable_chunked_prefill": self.config.enable_chunked_prefill,
"max_num_batched_tokens": self.config.max_num_batched_tokens,
"enable_prefix_caching": self.config.enable_prefix_caching,
"enable_sleep_mode": True,
"enable_sleep_mode": enable_sleep_mode,
"disable_custom_all_reduce": True,
"enforce_eager": self.config.enforce_eager,
"gpu_memory_utilization": self.config.gpu_memory_utilization,
Expand Down