0.06.116.694 I load_tensors: offloaded 47/47 layers to GPU
0.06.116.700 I load_tensors:        CUDA0 model buffer size = 56778.75 MiB
0.06.116.700 I load_tensors:        CUDA1 model buffer size = 58003.68 MiB
0.12.798.199 I llama_context:  CUDA_Host  output buffer size =     0.59 MiB
0.12.803.478 I llama_kv_cache:      CUDA0 KV buffer size =  1536.00 MiB
0.12.804.618 I llama_kv_cache:      CUDA1 KV buffer size =  1280.00 MiB
0.12.805.728 I llama_memory_recurrent:      CUDA0 RS buffer size =   308.25 MiB
0.12.806.019 I llama_memory_recurrent:      CUDA1 RS buffer size =   274.00 MiB
0.12.811.147 I llama_kv_cache:      CUDA0 KV buffer size =  1152.00 MiB
0.12.812.021 I llama_kv_cache:      CUDA1 KV buffer size =   960.00 MiB
0.12.879.104 I sched_reserve:      CUDA0 compute buffer size =   611.15 MiB
0.12.879.110 I sched_reserve:      CUDA1 compute buffer size =   611.10 MiB
0.12.879.110 I sched_reserve:  CUDA_Host compute buffer size =    86.77 MiB
0.12.986.696 I llama_context:  CUDA_Host  output buffer size =     0.59 MiB
0.12.991.561 I llama_kv_cache:      CUDA1 KV buffer size =   256.00 MiB
0.12.996.691 I llama_kv_cache:      CUDA1 KV buffer size =   192.00 MiB
0.13.049.284 I sched_reserve:      CUDA0 compute buffer size =     2.00 MiB
0.13.049.291 I sched_reserve:      CUDA1 compute buffer size =   598.83 MiB
0.13.049.292 I sched_reserve:  CUDA_Host compute buffer size =    84.77 MiB
0.13.116.350 I sched_reserve:      CUDA0 compute buffer size =     2.00 MiB
0.13.116.354 I sched_reserve:      CUDA1 compute buffer size =   598.83 MiB
0.13.116.354 I sched_reserve:  CUDA_Host compute buffer size =    84.77 MiB
0.14.976.241 I sched_reserve:      CUDA0 compute buffer size =   611.15 MiB
0.14.976.247 I sched_reserve:      CUDA1 compute buffer size =   611.10 MiB
0.14.976.248 I sched_reserve:  CUDA_Host compute buffer size =    86.77 MiB
