{ "execution_mode": "CPU algorithm with controlled inputs; any latency/capacity coefficients are assumptions", "workload_requests": 32, "hot_prefix_tokens": 4096, "user_turn_tokens": 256, "radix_split_demo": { "first_insert": { "matched_tokens": 0, "new_tokens": 8, "cached_tokens": 8 }, "second_insert": { "matched_tokens": 6, "new_tokens": 2, "cached_tokens": 10 } }, "policies": { "round_robin": { "policy": "round_robin", "total_requests": 32, "cache_hit_ratio": 0.7353, "mean_ttft_ms": 47.19, "max_ttft_ms": 108.8, "max_replica_requests": 8, "min_replica_requests": 8, "total_evicted_tokens": 3072, "replica_loads": [ { "replica_id": 0, "routed_requests": 8, "cached_tokens": 9216, "evicted_tokens": 1024 }, { "replica_id": 1, "routed_requests": 8, "cached_tokens": 6144, "evicted_tokens": 0 }, { "replica_id": 2, "routed_requests": 8, "cached_tokens": 9216, "evicted_tokens": 1024 }, { "replica_id": 3, "routed_requests": 8, "cached_tokens": 9216, "evicted_tokens": 1024 } ] }, "pure_affinity": { "policy": "pure_affinity", "total_requests": 32, "cache_hit_ratio": 0.4412, "mean_ttft_ms": 1217.24, "max_ttft_ms": 1625.6, "max_replica_requests": 32, "min_replica_requests": 0, "total_evicted_tokens": 69632, "replica_loads": [ { "replica_id": 0, "routed_requests": 32, "cached_tokens": 8192, "evicted_tokens": 69632 }, { "replica_id": 1, "routed_requests": 0, "cached_tokens": 0, "evicted_tokens": 0 }, { "replica_id": 2, "routed_requests": 0, "cached_tokens": 0, "evicted_tokens": 0 }, { "replica_id": 3, "routed_requests": 0, "cached_tokens": 0, "evicted_tokens": 0 } ] }, "cache_aware": { "policy": "cache_aware", "total_requests": 32, "cache_hit_ratio": 0.8235, "mean_ttft_ms": 32.34, "max_ttft_ms": 108.8, "max_replica_requests": 20, "min_replica_requests": 4, "total_evicted_tokens": 0, "replica_loads": [ { "replica_id": 0, "routed_requests": 4, "cached_tokens": 5120, "evicted_tokens": 0 }, { "replica_id": 1, "routed_requests": 20, "cached_tokens": 9216, "evicted_tokens": 0 }, { "replica_id": 2, "routed_requests": 4, "cached_tokens": 5120, "evicted_tokens": 0 }, { "replica_id": 3, "routed_requests": 4, "cached_tokens": 5120, "evicted_tokens": 0 } ] } } }