Skip to content

Super tiny remove unused select_worker_pair #14609

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
slin1237 merged 2 commits into from
Dec 8, 2025
Merged

Super tiny remove unused select_worker_pair #14609

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
f970cf8
more
fzyzcjy Dec 8, 2025
79bfded
Merge branch 'main' into feat/rm_pair
slin1237 Dec 8, 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
19 changes: 0 additions & 19 deletions sgl-model-gateway/src/policies/bucket.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -312,25 +312,6 @@ impl LoadBalancingPolicy for BucketPolicy {
workers.iter().position(|w| w.url() == prefill_url)
}

fn select_worker_pair(
&self,
prefill_workers: &[Arc<dyn Worker>],
decode_workers: &[Arc<dyn Worker>],
request_text: Option<&str>,
) -> Option<(usize, usize)> {
let prefill_idx = self.select_worker(prefill_workers, request_text)?;

let healthy_decode = get_healthy_worker_indices(decode_workers);
if healthy_decode.is_empty() {
return None;
}

let mut rng = rand::rng();
let decode_idx = rng.random_range(0..healthy_decode.len());

Some((prefill_idx, decode_idx))
}

fn name(&self) -> &'static str {
"bucket"
}
Expand Down
31 changes: 0 additions & 31 deletions sgl-model-gateway/src/policies/cache_aware.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -347,37 +347,6 @@ impl LoadBalancingPolicy for CacheAwarePolicy {
}
}

fn select_worker_pair(
&self,
prefill_workers: &[Arc<dyn Worker>],
decode_workers: &[Arc<dyn Worker>],
request_text: Option<&str>,
) -> Option<(usize, usize)> {
// DEPRECATED: This method is no longer used when separate policies are configured.
// The PD router now uses separate policies for prefill and decode selection.
// This implementation remains for backward compatibility when a single policy is used.

// In PD mode with single policy:
// - Prefill: Use cache-aware routing for better cache utilization
// - Decode: Use least-load routing for better load distribution

// Select prefill worker using cache-aware logic
let prefill_idx = self.select_worker(prefill_workers, request_text)?;

// Select decode worker using least-load logic
let healthy_decode = get_healthy_worker_indices(decode_workers);
if healthy_decode.is_empty() {
return None;
}

let decode_idx = healthy_decode
.iter()
.min_by_key(|&&idx| decode_workers[idx].load())
.copied()?;

Some((prefill_idx, decode_idx))
}

fn on_request_complete(&self, worker_url: &str, success: bool) {
// Could track success rates per worker for more intelligent routing
if !success {
Expand Down
16 changes: 0 additions & 16 deletions sgl-model-gateway/src/policies/mod.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -39,22 +39,6 @@ pub trait LoadBalancingPolicy: Send + Sync + Debug {
request_text: Option<&str>,
) -> Option<usize>;

/// Select a pair of workers (prefill and decode) for PD routing
///
/// Returns indices of (prefill_worker, decode_worker) from their respective arrays.
/// Default implementation uses select_worker for each array independently.
fn select_worker_pair(
&self,
prefill_workers: &[Arc<dyn Worker>],
decode_workers: &[Arc<dyn Worker>],
request_text: Option<&str>,
) -> Option<(usize, usize)> {
// Default implementation: independently select from each pool
let prefill_idx = self.select_worker(prefill_workers, request_text)?;
let decode_idx = self.select_worker(decode_workers, request_text)?;
Some((prefill_idx, decode_idx))
}

/// Update policy state after request completion
///
/// This is called when a request completes (successfully or not) to allow
Expand Down
Loading