feat: update ttft modeling and add cache affinity

src/hardware_presets.rs

@@ -188,10 +188,14 @@ fn make_config(n: u32, base: &GpuBase) -> HardwareConfig {
         gpu_mem_bw: base.mem_bw * f,
         hbm_bytes: base.hbm * f,
         dram_bytes: dram,
+        host_dram_bw: if n >= 8 { 9.0e11 } else { 5.0e11 },
         pcie_bw: pcie_per_gpu * f,
         pcie_latency_us: pcie_lat,
         rdma_bw: rdma_base * rdma_scale,
         rdma_latency_us: rdma_lat,
+        intra_node_tp_bw: if base.pcie_gen >= 6 { 1.8e12 * f } else { 9.0e11 * f },
+        intra_node_tp_latency_us: if base.pcie_gen >= 6 { 1.0 } else { 2.0 },
+        tp_degree: n,
         max_batch_slots: 256,
         prefill_chunk_tokens: if n >= 4 { 4096 } else { 2048 },
     }