0.07.816.846 I load_tensors: offloaded 47/47 layers to GPU
0.07.816.852 I load_tensors:        CUDA0 model buffer size = 74114.91 MiB
0.07.816.852 I load_tensors:        CUDA1 model buffer size = 75433.28 MiB
0.16.516.446 I llama_context:  CUDA_Host  output buffer size =     0.59 MiB
0.16.522.208 I llama_kv_cache:      CUDA0 KV buffer size =  1536.00 MiB
0.16.523.362 I llama_kv_cache:      CUDA1 KV buffer size =  1280.00 MiB
0.16.524.476 I llama_memory_recurrent:      CUDA0 RS buffer size =   308.25 MiB
0.16.524.763 I llama_memory_recurrent:      CUDA1 RS buffer size =   274.00 MiB
0.16.529.720 I llama_kv_cache:      CUDA0 KV buffer size =  1152.00 MiB
0.16.530.590 I llama_kv_cache:      CUDA1 KV buffer size =   960.00 MiB
0.16.599.143 I sched_reserve:      CUDA0 compute buffer size =   611.15 MiB
0.16.599.149 I sched_reserve:      CUDA1 compute buffer size =   611.10 MiB
0.16.599.150 I sched_reserve:  CUDA_Host compute buffer size =    86.77 MiB
0.16.709.828 I llama_context:  CUDA_Host  output buffer size =     0.59 MiB
0.16.714.685 I llama_kv_cache:      CUDA1 KV buffer size =   256.00 MiB
0.16.719.721 I llama_kv_cache:      CUDA1 KV buffer size =   192.00 MiB
0.16.771.839 I sched_reserve:      CUDA0 compute buffer size =     2.00 MiB
0.16.771.845 I sched_reserve:      CUDA1 compute buffer size =   598.83 MiB
0.16.771.846 I sched_reserve:  CUDA_Host compute buffer size =    84.77 MiB
0.16.839.372 I sched_reserve:      CUDA0 compute buffer size =     2.00 MiB
0.16.839.376 I sched_reserve:      CUDA1 compute buffer size =   598.83 MiB
0.16.839.377 I sched_reserve:  CUDA_Host compute buffer size =    84.77 MiB
0.18.703.667 I sched_reserve:      CUDA0 compute buffer size =   611.15 MiB
0.18.703.673 I sched_reserve:      CUDA1 compute buffer size =   611.10 MiB
0.18.703.674 I sched_reserve:  CUDA_Host compute buffer size =    86.77 MiB
