Expose the real-time internal state of the batcher through SSE #3065
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
co42
reviewed
Feb 28, 2025
| @@ -112,6 +136,10 @@ impl Backend for BackendV3 { | |||
| .is_ok() | |||
| } | |||
|
|
|||
| fn events(&self) -> BroadcastReceiver<EngineState> { | |||
| self.state_events.0.subscribe() | |||
There was a problem hiding this comment.
You should send the current state as soon as a new connection is open (new subscribe)
| let stream = infer.events(); | ||
| let sse = | ||
| Sse::new(BroadcastStream::from(stream).map(|state| { | ||
| Event::default().json_data(state.map_err(|err| axum::Error::new(err))?) |
Comment on lines
+155
to
+172
| // Dispatch new state to the proxy | ||
| { | ||
| // Lock free operation (read) | ||
| let num_queued_tokens = engine_state.read().await.in_queue; | ||
| { | ||
| // Critical section, doing as little as possible here | ||
| let mut engine_state = engine_state.write().await; | ||
| engine_state.in_queue = num_queued_tokens + entry_num_tokens; | ||
| } | ||
|
|
||
| // Send new state to the channel for broadcasting | ||
| if let Err(err) = queue_events.send(*engine_state.read().await) { | ||
| tracing::warn!( | ||
| "Failed to send BatchEvent::QueueChanged({}): {err}", | ||
| num_queued_tokens + entry_num_tokens | ||
| ) | ||
| } | ||
| } |
There was a problem hiding this comment.
Suggested change
| // Dispatch new state to the proxy | |
| { | |
| // Lock free operation (read) | |
| let num_queued_tokens = engine_state.read().await.in_queue; | |
| { | |
| // Critical section, doing as little as possible here | |
| let mut engine_state = engine_state.write().await; | |
| engine_state.in_queue = num_queued_tokens + entry_num_tokens; | |
| } | |
| // Send new state to the channel for broadcasting | |
| if let Err(err) = queue_events.send(*engine_state.read().await) { | |
| tracing::warn!( | |
| "Failed to send BatchEvent::QueueChanged({}): {err}", | |
| num_queued_tokens + entry_num_tokens | |
| ) | |
| } | |
| } | |
| engine_state.modify(|state| state.in_queue += entry_num_tokens); |
Function modify then send the new state in the SSE
# for free
to join this conversation on GitHub.
Already have an account?
# to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
No description provided.