aibridge: LRU embed cache - 236x RPS gain on warm workloads. Per architecture_comparison.md universal-win for Rust side. Cache key (model,text), default 4096 entries, in-process inside gateway. Load test: 128 RPS -> 30k+ RPS, p50 78ms -> 129us.

2026-05-01 04:45:20 -05:00
parent 9eed982f1a
commit 150cc3b681
3 changed files with 165 additions and 1 deletions
@@ -48,6 +48,7 @@ version = "0.1.0"
 dependencies = [
 "async-trait",
 "axum",
+ "lru",
 "reqwest",
 "serde",
 "serde_json",