Skip to content

fix(vllm_omni): default collective group communication backend #505

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

Open
lrq619 wants to merge 1 commit into
base: main
Choose a base branch
from
+9 −2
Open

fix(vllm_omni): default collective group communication backend #505

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
11 changes: 9 additions & 2 deletions roll/distributed/strategy/vllm_omni_strategy.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -320,9 +320,16 @@ async def process_weights_after_loading(self, *args, **kwargs):
# going through strategy.load_states(); keep strategy state in sync.
self.is_model_in_gpu = True

async def setup_collective_group(self, *args, **kwargs):
async def setup_collective_group(self, master_address, master_port, rank_offset, world_size, group_name, backend=None):
if hasattr(self.model, "setup_collective_group"):
await self.model.setup_collective_group(*args, **kwargs)
await self.model.setup_collective_group(
master_address=master_address,
master_port=master_port,
rank_offset=rank_offset,
world_size=world_size,
group_name=group_name,
backend=backend if backend is not None else current_platform.communication_backend,
)

async def broadcast_parameter(self, *args, **kwargs):
if hasattr(self.model, "broadcast_parameter"):
Expand Down
Loading