Update _posts/2025-10-25-semantic-router-modular.md

Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>

Author: Xunzhuo

_posts/2025-10-25-semantic-router-modular.md

@@ -54,13 +54,13 @@ The base model runs once, producing intermediate representations. Each LoRA adap
 
 The implementation in parallel_engine.rs uses [Rayon](https://github.com/rayon-rs/rayon) for data parallelism, processing multiple LoRA adapters concurrently. For a request requiring three classifications, this changes the workload from three full forward passes to one full pass plus three lightweight adapter applications.
 
-## Concurrency Through OnceLock
+## Concurrency Through `OnceLock`
 
-The previous implementation used lazy_static for managing global classifier state, which introduced lock contention under concurrent load. The refactoring replaces this with [OnceLock](https://doc.rust-lang.org/std/sync/struct.OnceLock.html) from the Rust standard library.
+The previous implementation used `lazy_static` for managing global classifier state, which introduced lock contention under concurrent load. The refactoring replaces this with [`OnceLock`](https://doc.rust-lang.org/std/sync/struct.OnceLock.html) from the Rust standard library.
 
-OnceLock provides lock-free reads after initialization. After the first initialization, all subsequent accesses are simple pointer reads with no synchronization overhead. Tests in oncelock_concurrent_test.rs verify this with 10 concurrent threads performing 30 total classifications, confirming that throughput scales linearly with thread count.
+`OnceLock` provides lock-free reads after initialization. After the first initialization, all subsequent accesses are simple pointer reads with no synchronization overhead. Tests in `oncelock_concurrent_test.rs` verify this with 10 concurrent threads performing 30 total classifications, confirming that throughput scales linearly with thread count.
 
-This matters when the router processes multiple incoming requests. With lazy_static, concurrent requests would queue behind a mutex. With OnceLock, they execute in parallel without contention.
+This matters when the router processes multiple incoming requests. With `lazy_static`, concurrent requests would queue behind a mutex. With `OnceLock`, they execute in parallel without contention.
 
 ### Flash Attention for GPU Acceleration