Skip to content
Closed
Changes from all commits
Commits
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: 7 additions & 0 deletions src/forge/controller/provisioner.py
Original file line number Diff line number Diff line change
Expand Up @@ -27,6 +27,8 @@
logger = logging.getLogger(__name__)
logger.setLevel(logging.DEBUG)

_ENV_VARS_TO_INHERIT = ["TORCHSTORE_RDMA_ENABLED"]


def _get_port() -> str:
with socket.socket(socket.AF_INET, socket.SOCK_STREAM) as s:
Expand Down Expand Up @@ -241,6 +243,11 @@ def bootstrap(env: dict[str, str]):
# Shows detailed logs for Monarch rust failures
env_vars["RUST_BACKTRACE"] = "1"

for name in _ENV_VARS_TO_INHERIT:
val = os.environ.get(name)
if val is not None:
env_vars[name] = val

procs = host_mesh.spawn_procs(
per_host={"gpus": num_procs},
bootstrap=functools.partial(bootstrap, env=env_vars),
Expand Down
Loading