0.07.791.455 I load_tensors: offloaded 47/47 layers to GPU
0.07.791.461 I load_tensors:        CUDA0 model buffer size = 74114.91 MiB
0.07.791.462 I load_tensors:        CUDA1 model buffer size = 71966.25 MiB
0.16.343.768 I llama_context:  CUDA_Host  output buffer size =     0.59 MiB
0.16.349.052 I llama_kv_cache:      CUDA0 KV buffer size =  1536.00 MiB
0.16.350.192 I llama_kv_cache:      CUDA1 KV buffer size =  1280.00 MiB
0.16.351.171 I llama_memory_recurrent:      CUDA0 RS buffer size =    77.06 MiB
0.16.351.295 I llama_memory_recurrent:      CUDA1 RS buffer size =    68.50 MiB
0.16.356.527 I llama_kv_cache:      CUDA0 KV buffer size =  1152.00 MiB
0.16.357.397 I llama_kv_cache:      CUDA1 KV buffer size =   960.00 MiB
0.16.424.823 I sched_reserve:      CUDA0 compute buffer size =   611.15 MiB
0.16.424.829 I sched_reserve:      CUDA1 compute buffer size =   611.10 MiB
0.16.424.830 I sched_reserve:  CUDA_Host compute buffer size =    86.77 MiB
