0.06.111.934 I load_tensors: offloaded 47/47 layers to GPU
0.06.111.939 I load_tensors:        CUDA0 model buffer size = 56778.75 MiB
0.06.111.940 I load_tensors:        CUDA1 model buffer size = 58003.68 MiB
0.12.939.240 I llama_context:  CUDA_Host  output buffer size =     0.59 MiB
0.12.939.897 I llama_kv_cache:      CUDA0 KV buffer size =   240.00 MiB
0.12.940.132 I llama_kv_cache:      CUDA1 KV buffer size =   200.00 MiB
0.12.940.602 I llama_memory_recurrent:      CUDA0 RS buffer size =   308.25 MiB
0.12.940.892 I llama_memory_recurrent:      CUDA1 RS buffer size =   274.00 MiB
0.12.941.595 I llama_kv_cache:      CUDA0 KV buffer size =   180.00 MiB
0.12.941.848 I llama_kv_cache:      CUDA1 KV buffer size =   150.00 MiB
0.12.983.307 I sched_reserve:      CUDA0 compute buffer size =   109.33 MiB
0.12.983.314 I sched_reserve:      CUDA1 compute buffer size =   109.28 MiB
0.12.983.314 I sched_reserve:  CUDA_Host compute buffer size =    16.95 MiB
0.13.094.991 I llama_context:  CUDA_Host  output buffer size =     0.59 MiB
0.13.095.907 I llama_kv_cache:      CUDA1 KV buffer size =    40.00 MiB
0.13.096.761 I llama_kv_cache:      CUDA1 KV buffer size =    30.00 MiB
0.13.119.120 I sched_reserve:      CUDA0 compute buffer size =     2.00 MiB
0.13.119.125 I sched_reserve:      CUDA1 compute buffer size =    97.01 MiB
0.13.119.125 I sched_reserve:  CUDA_Host compute buffer size =    14.95 MiB
0.13.144.924 I sched_reserve:      CUDA0 compute buffer size =     2.00 MiB
0.13.144.928 I sched_reserve:      CUDA1 compute buffer size =    97.01 MiB
0.13.144.929 I sched_reserve:  CUDA_Host compute buffer size =    14.95 MiB
0.15.077.887 I sched_reserve:      CUDA0 compute buffer size =   109.33 MiB
0.15.077.892 I sched_reserve:      CUDA1 compute buffer size =   109.28 MiB
0.15.077.893 I sched_reserve:  CUDA_Host compute buffer size =    16.95 MiB
