[model-gateway] Add PrefixHash load balancing policy for KV cache-aware routing (#15935)

2025-12-27 05:58:05 -05:00
parent ca740a41f3
commit 3645ed0f73
14 changed files with 532 additions and 60 deletions
@@ -50,6 +50,8 @@ futures = "0.3"
 dashmap = "6.1.0"
 lru = "0.16.2"
 blake3 = "1.5"
+xxhash-rust = { version = "0.8", features = ["xxh3"] }
+bytemuck = { version = "1.21", features = ["derive"] }
 http = "1.1.0"
 tokio = { version = "1.42.0", features = ["full"] }
 async-trait = "0.1"