Skip to content

feat: FT Request Cancellation feature and test for 0.5.0 #2500

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
nnshah1 merged 11 commits into from
Sep 2, 2025
Merged

feat: FT Request Cancellation feature and test for 0.5.0 #2500

Changes from 1 commit
Commits
Show all changes
11 commits
Select commit Hold shift + click to select a range
4fcb1c5
fix: Relay engine_ctx between streams
kthui Aug 2, 2025
1c8188a
fix: Retain context_id between requests
kthui Aug 13, 2025
8f12b18
debug: Add debug print on received migration limit
kthui Aug 7, 2025
e75ca6d
feat: FT Python Context and Unit Tests (#2677)
kthui Aug 25, 2025
b4603fa
feat: vLLM abort on stream stop (#2717)
kthui Aug 26, 2025
2678c5b
test: HTTP Request Cancellation E2E Testing (#2350)
kthui Aug 26, 2025
d5a5a5c
docs: Request Cancellation
kthui Aug 27, 2025
29b3829
Pass context as kwargs
kthui Aug 27, 2025
a0047e2
Enhance stop stop_generating and kill methods logic
kthui Aug 27, 2025
8b06e6c
docs: Remove Future Roadmap section
kthui Aug 28, 2025
ba47834
test: Combine NATS and ETCD start/stop into conftest.py
kthui Aug 28, 2025
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
Prev Previous commit
Next Next commit
debug: Add debug print on received migration limit
  • Loading branch information
@kthui
kthui committed Aug 25, 2025
commit 8f12b181bd138aabddcb5b10a434ffb58b959938
5 changes: 5 additions & 0 deletions lib/llm/src/migration.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -29,6 +29,11 @@ pub struct Migration {

impl Migration {
pub async fn from_mdc(mdc: ModelDeploymentCard) -> Result<Arc<Self>> {
tracing::debug!(
"model {} migration limit {}",
mdc.display_name,
mdc.migration_limit
);
Ok(Arc::new(Self {
migration_limit: mdc.migration_limit,
}))
Expand Down
Loading