0.06.327.171 I load_tensors: offloaded 47/47 layers to GPU
0.06.327.176 I load_tensors:        CUDA0 model buffer size = 56778.75 MiB
0.06.327.177 I load_tensors:        CUDA1 model buffer size = 55333.42 MiB
0.12.923.250 I llama_context:  CUDA_Host  output buffer size =     0.59 MiB
0.12.923.983 I llama_kv_cache:      CUDA0 KV buffer size =   240.00 MiB
0.12.924.232 I llama_kv_cache:      CUDA1 KV buffer size =   200.00 MiB
0.12.924.533 I llama_memory_recurrent:      CUDA0 RS buffer size =    77.06 MiB
0.12.924.666 I llama_memory_recurrent:      CUDA1 RS buffer size =    68.50 MiB
0.12.925.380 I llama_kv_cache:      CUDA0 KV buffer size =   180.00 MiB
0.12.925.605 I llama_kv_cache:      CUDA1 KV buffer size =   150.00 MiB
0.12.961.842 I sched_reserve:      CUDA0 compute buffer size =   109.33 MiB
0.12.961.845 I sched_reserve:      CUDA1 compute buffer size =   109.28 MiB
0.12.961.846 I sched_reserve:  CUDA_Host compute buffer size =    16.95 MiB
