0.08.071.336 I load_tensors: offloaded 47/47 layers to GPU
0.08.071.343 I load_tensors:        CUDA0 model buffer size = 74114.91 MiB
0.08.071.343 I load_tensors:        CUDA1 model buffer size = 75433.28 MiB
0.16.776.998 I llama_context:  CUDA_Host  output buffer size =     0.59 MiB
0.16.777.730 I llama_kv_cache:      CUDA0 KV buffer size =   240.00 MiB
0.16.777.983 I llama_kv_cache:      CUDA1 KV buffer size =   200.00 MiB
0.16.778.462 I llama_memory_recurrent:      CUDA0 RS buffer size =   308.25 MiB
0.16.778.756 I llama_memory_recurrent:      CUDA1 RS buffer size =   274.00 MiB
0.16.779.423 I llama_kv_cache:      CUDA0 KV buffer size =   180.00 MiB
0.16.779.640 I llama_kv_cache:      CUDA1 KV buffer size =   150.00 MiB
0.16.817.388 I sched_reserve:      CUDA0 compute buffer size =   109.33 MiB
0.16.817.391 I sched_reserve:      CUDA1 compute buffer size =   109.28 MiB
0.16.817.392 I sched_reserve:  CUDA_Host compute buffer size =    16.95 MiB
0.16.923.237 I llama_context:  CUDA_Host  output buffer size =     0.59 MiB
0.16.924.134 I llama_kv_cache:      CUDA1 KV buffer size =    40.00 MiB
0.16.924.976 I llama_kv_cache:      CUDA1 KV buffer size =    30.00 MiB
0.16.947.216 I sched_reserve:      CUDA0 compute buffer size =     2.00 MiB
0.16.947.220 I sched_reserve:      CUDA1 compute buffer size =    97.01 MiB
0.16.947.220 I sched_reserve:  CUDA_Host compute buffer size =    14.95 MiB
0.16.972.960 I sched_reserve:      CUDA0 compute buffer size =     2.00 MiB
0.16.972.965 I sched_reserve:      CUDA1 compute buffer size =    97.01 MiB
0.16.972.965 I sched_reserve:  CUDA_Host compute buffer size =    14.95 MiB
0.18.913.397 I sched_reserve:      CUDA0 compute buffer size =   109.33 MiB
0.18.913.402 I sched_reserve:      CUDA1 compute buffer size =   109.28 MiB
0.18.913.402 I sched_reserve:  CUDA_Host compute buffer size =    16.95 MiB
