style: cargo fmt --workspace (whitespace/wrapping only, no semantic change)

Whole-workspace rustfmt pass picked up while iterating on Mamba GPU
backward work. Verified formatting-only via diff sampling; no logic
changed.

Co-Authored-By: Claude Sonnet 5 <[email protected]>

crates/production/rtx-inference/src/speculative/eagle3.rs

@@ -128,8 +128,7 @@ impl DynamicDraftTree {
         if self.config.max_depth == 0 {
             return false;
         }
-        node.probability > self.config.expansion_threshold
-            && node.depth < self.config.max_depth - 1
+        node.probability > self.config.expansion_threshold && node.depth < self.config.max_depth - 1
     }
 
     /// Remove all leaf nodes whose cumulative path probability (root→leaf
@@ -237,9 +236,10 @@ impl DynamicDraftTree {
                         if let Some(parent_idx) = self.inner.nodes[idx].parent {
                             let siblings: Vec<usize> =
                                 self.inner.nodes[parent_idx].children.clone();
-                            if let Some(sibling_idx) = siblings.into_iter().find(|&s| {
-                                self.inner.nodes[s].token_id == actual_next_token
-                            }) {
+                            if let Some(sibling_idx) = siblings
+                                .into_iter()
+                                .find(|&s| self.inner.nodes[s].token_id == actual_next_token)
+                            {
                                 self.inner.nodes[sibling_idx].accepted = true;
                                 accepted += 1;
                             }
@@ -332,10 +332,8 @@ impl Eagle3Decoder {
             .draft_from_hidden(hidden_states, context, &eagle_cfg)
             .await?;
 
-        let root_candidates: Vec<(u32, f32)> = root_tokens
-            .iter()
-            .map(|t| (t.id, t.probability))
-            .collect();
+        let root_candidates: Vec<(u32, f32)> =
+            root_tokens.iter().map(|t| (t.id, t.probability)).collect();
 
         let root_indices = tree.add_roots(&root_candidates);
 
@@ -369,22 +367,17 @@ impl Eagle3Decoder {
         } {
             let node_depth = tree.inner.nodes[parent_idx].depth;
             // Force expansion until each path is at least min_depth tokens.
-            let must_expand = self.config.min_depth > 0
-                && node_depth < self.config.min_depth - 1;
+            let must_expand = self.config.min_depth > 0 && node_depth < self.config.min_depth - 1;
             let may_expand = tree.should_expand(parent_idx);
 
             if !must_expand && !may_expand {
                 continue;
             }
 
-            let child_tokens = draft_model
-                .draft_from_hidden(&hs, &ctx, &eagle_cfg)
-                .await?;
+            let child_tokens = draft_model.draft_from_hidden(&hs, &ctx, &eagle_cfg).await?;
 
-            let child_candidates: Vec<(u32, f32)> = child_tokens
-                .iter()
-                .map(|t| (t.id, t.probability))
-                .collect();
+            let child_candidates: Vec<(u32, f32)> =
+                child_tokens.iter().map(|t| (t.id, t.probability)).collect();
 
             let child_indices = tree.expand_node(parent_idx, &child_candidates);
 
@@ -414,9 +407,9 @@ impl Eagle3Decoder {
 #[cfg(test)]
 mod tests {
     use super::*;
+    use crate::InferenceResult;
     use crate::speculative::eagle::{EagleConfig, EagleDraftModel};
     use crate::speculative::types::Token;
-    use crate::InferenceResult;
 
     // -----------------------------------------------------------------------
     // Mock EagleDraftModel
@@ -638,10 +631,7 @@ mod tests {
 
         let prob = tree.path_probability(gc);
         // 0.8 * 0.5 * 0.25 = 0.1
-        assert!(
-            (prob - 0.1_f32).abs() < 1e-6,
-            "expected 0.1, got {prob}"
-        );
+        assert!((prob - 0.1_f32).abs() < 1e-6, "expected 0.1, got {prob}");
     }
 
     // -----------------------------------------------------------------------

crates/production/rtx-inference/src/speculative/metrics.rs

@@ -103,10 +103,7 @@ impl WindowedAcceptanceTracker {
         if self.buffer.is_empty() {
             return 0.0;
         }
-        self.buffer
-            .iter()
-            .copied()
-            .fold(f32::INFINITY, f32::min)
+        self.buffer.iter().copied().fold(f32::INFINITY, f32::min)
     }
 
     /// Maximum value in the current window, or `0.0` if empty.
@@ -266,8 +263,7 @@ impl PerformanceMetrics {
         };
 
         // Push per-step acceptance rate into the sliding window.
-        let step_rate =
-            step_result.accepted_tokens as f32 / step_result.draft_tokens.max(1) as f32;
+        let step_rate = step_result.accepted_tokens as f32 / step_result.draft_tokens.max(1) as f32;
         self.windowed.push(step_rate);
 
         // Estimate speedup ratio
@@ -338,10 +334,7 @@ mod tests {
         assert!(tracker.is_full());
         // Sum should be 0.2 + 0.3 + 0.4 = 0.9 → mean ≈ 0.3
         let rate = tracker.windowed_rate();
-        assert!(
-            (rate - 0.3).abs() < 1e-5,
-            "expected ~0.3, got {rate}"
-        );
+        assert!((rate - 0.3).abs() < 1e-5, "expected ~0.3, got {rate}");
     }
 
     #[test]
@@ -438,8 +431,16 @@ mod tests {
         tracker.push(0.3);
         tracker.push(0.7);
         tracker.push(0.9);
-        assert!((tracker.min() - 0.3).abs() < 1e-5, "min got {}", tracker.min());
-        assert!((tracker.max() - 0.9).abs() < 1e-5, "max got {}", tracker.max());
+        assert!(
+            (tracker.min() - 0.3).abs() < 1e-5,
+            "min got {}",
+            tracker.min()
+        );
+        assert!(
+            (tracker.max() - 0.9).abs() < 1e-5,
+            "max got {}",
+            tracker.max()
+        );
     }
 
     #[test]
@@ -455,7 +456,7 @@ mod tests {
     fn test_clamp_out_of_range() {
         let mut tracker = WindowedAcceptanceTracker::new(5);
         tracker.push(-0.5); // clamped to 0.0
-        tracker.push(1.5);  // clamped to 1.0
+        tracker.push(1.5); // clamped to 1.0
         assert!((tracker.windowed_rate() - 0.5).abs() < 1e-5);
     }
 }

crates/production/rtx-inference/src/speculative/mod.rs

@@ -49,7 +49,7 @@ pub use medusa::*;
 pub use metrics::*;
 pub use self_spec::*;
 pub use streaming::{
-    collect_stream, SpeculativeStreamConfig, SpeculativeStreamer, StreamStats, StreamedToken,
+    SpeculativeStreamConfig, SpeculativeStreamer, StreamStats, StreamedToken, collect_stream,
 };
 pub use traits::*;
 pub use tree::*;