Skip to content

fix: Minor fix to "fix: Evict inference request internal release callback after invoking (#452)" #454

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
merged 1 commit into from
Oct 2, 2025
Merged

fix: Minor fix to "fix: Evict inference request internal release callback after invoking (#452)" #454

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
8 changes: 3 additions & 5 deletions src/infer_request.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -476,10 +476,9 @@ InferenceRequest::Release(
std::unique_ptr<InferenceRequest>&& request, const uint32_t release_flags)
{
// Invoke the release callbacks added internally before releasing the
// request to user provided callback.

// Invoke callbacks in reverse order. Evict internal callbacks for reusing
// inference request object.
// request to user provided callback. Remove internal callbacks registered
// through AddInternalReleaseCallback to allow reuse of the inference request
// object.
auto& release_callbacks = request->release_callbacks_;
for (int i = release_callbacks.size() - 1; i >= 0; --i) {
auto [release_fn, is_internal] = release_callbacks[i];
Expand Down Expand Up @@ -508,7 +507,6 @@ InferenceRequest::Release(
"Failed to set released state");
void* userp = request->release_userp_;
auto& release_fn = request->release_fn_;
LOG_INFO << "userp " << userp << std::endl;
release_fn(
reinterpret_cast<TRITONSERVER_InferenceRequest*>(request.release()),
release_flags, userp);
Expand Down