feat: update ttft modeling and add cache affinity

2026-04-15 19:08:10 +08:00
parent ff316c6873
commit a3f386c858
15 changed files with 1276 additions and 99 deletions
--- a/tests/smoke.rs
+++ b/tests/smoke.rs
@@ -28,13 +28,18 @@ fn base_config(trace_path: &str, out_dir: &str, mode: RouterMode) -> Config {
            gpu_mem_bw: 1.0e12,
            hbm_bytes: 1.0e9,
            dram_bytes: 4.0e9,
+            host_dram_bw: 5.0e11,
            pcie_bw: 32.0e9,
            pcie_latency_us: 1.0,
            rdma_bw: 12.0e9,
            rdma_latency_us: 5.0,
+            intra_node_tp_bw: 9.0e11,
+            intra_node_tp_latency_us: 2.0,
+            tp_degree: 1,
            max_batch_slots: 32,
            prefill_chunk_tokens: 1024,
        },
+        calibration: CalibrationConfig::default(),
        cluster: ClusterConfig {
            num_instances: 4,
            meta_store: MetaStoreConfig {