Skip to content

fix(inference): adopt an interrupted managed vLLM container holding the serving port #11530

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
HOYALIM wants to merge 9 commits into
base: main
Choose a base branch
from
+9 −1
Open

fix(inference): adopt an interrupted managed vLLM container holding the serving port #11530

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
9 commits
Select commit Hold shift + click to select a range
f82b8d3
fix(inference): adopt an interrupted managed vLLM container holding t…
HOYALIM Sep 11, 2026
01be96c
fix(inference): require the adopted container to hold the failed port
HOYALIM Sep 11, 2026
52c4b37
fix(inference): keep adopted vLLM on local Docker
jyaunches Sep 11, 2026
452f254
merge: update main for validation
jyaunches Sep 11, 2026
baed467
fix(inference): match adopted vLLM binding address
jyaunches Sep 11, 2026
bf1b1d8
merge: update main for validation
jyaunches Sep 11, 2026
55b330e
merge: update PR base for E2E qualification
jyaunches Sep 11, 2026
44803ab
fix(inference): pin adopted port lookup to container ID
rsliter Sep 15, 2026
2c01fba
merge: refresh PR 11530 after confirmed conflict
rsliter Sep 15, 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
6 changes: 6 additions & 0 deletions src/lib/inference/vllm-serving-port.test.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -455,6 +455,12 @@ describe("managed vLLM serving-port guard (#8685)", () => {
MANAGED_CONTAINER_ID,
expect.objectContaining({ ignoreError: true, suppressOutput: true }),
);
expect(mocks.dockerCapture).toHaveBeenCalledWith(
["port", MANAGED_CONTAINER_ID, "8000"],
expect.objectContaining({
env: expect.objectContaining({ DOCKER_CONTEXT: "default" }),
}),
);
expect(mocks.dockerRunDetached).toHaveBeenCalled();
expect(errSpy.mock.calls.flat().join("\n")).not.toContain("another process");
const dockerOptions = [
Expand Down
4 changes: 3 additions & 1 deletion src/lib/inference/vllm.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1975,7 +1975,9 @@ function adoptableServingPortHolder(
const ownership = inspectVllmContainerOwnershipInDockerEnv(containerName, dockerEnv);
if (ownership.kind !== "managed" || !ownership.running) return undefined;
// The managed container always publishes the fixed container port 8000.
const published = dockerCapture(["port", containerName, "8000"], {
// Keep the binding lookup pinned to the identity that passed ownership
// inspection. The fixed name can change hands between Docker commands.
const published = dockerCapture(["port", ownership.containerId, "8000"], {
env: dockerEnv,
ignoreError: true,
timeout: 10_000,
Expand Down