Skip to content

Increase vLLM health timeout to 10 minutes #1452

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
hamishivi merged 2 commits into from
Feb 2, 2026
Merged

Increase vLLM health timeout to 10 minutes #1452

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
99ba478
Increase vLLM health check timeout to 10 minutes
hamishivi Feb 1, 2026
e9e3007
Merge branch 'main' into increase-vllm-health-timeout
hamishivi Feb 1, 2026
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
1 change: 1 addition & 0 deletions CHANGELOG.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -12,6 +12,7 @@ All notable changes to this project will be documented in this file.

### Changed

- Increased vLLM health check timeout from 30s to 600s (10 minutes) (https://github.com/allenai/open-instruct/pull/1452).
- Updated vllm version to 0.14.1 (https://github.com/allenai/open-instruct/pull/1433).
- Changed default wandb x-axis from `episode` to `training_step` for grpo_fast (https://github.com/allenai/open-instruct/pull/1437).

Expand Down
5 changes: 4 additions & 1 deletion open_instruct/vllm_utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -72,6 +72,7 @@
DRAIN_ACTIVE_TASKS_SLEEP_S = 1
SHOULD_STOP_TIMEOUT_S = 0.1
INFERENCE_INIT_TIMEOUT_S = 1200
VLLM_HEALTH_CHECK_TIMEOUT_S = 600.0


def model_dims_from_vllm_config(vllm_config: "vllm.config.VllmConfig") -> ModelDims:
Expand Down Expand Up @@ -435,7 +436,9 @@ def init_process_group(
async def _check_health(port: int) -> None:
async with (
aiohttp.ClientSession() as session,
session.get(f"http://127.0.0.1:{port}/health", timeout=aiohttp.ClientTimeout(total=30.0)) as response,
session.get(
f"http://127.0.0.1:{port}/health", timeout=aiohttp.ClientTimeout(total=VLLM_HEALTH_CHECK_TIMEOUT_S)
) as response,
):
if response.status != 200:
raise RuntimeError(f"vLLM server health check failed with status {response.status}")
Expand Down