Long context models don't split memory correctly leads to OOM error

### What is the issue? Using mixtral default 2048 ctx splits memory across 2x GPUs ~12 GBs each. When extending context to 12k, it dumps all mem on one GPU using 29 GB. Ideally, would want to split equally as before to push to higher 16k context without OOM. Using 2x 48 GB A6000. Issue is possibly related to https://github.com/ollama/ollama/issues/1341 ``` [GIN] 2024/05/05 - 23:38:16 | 200 | 24.89660366s | 172.17.0.1 | POST "/api/chat" {"function":"process_single_task","level":"INFO","line":1506,"msg":"slot data","n_idle_slots":1,"n_processing_slots":0,"task_id":42754,"tid":"139643039125504","timestamp":1714977496} {"function":"log_server_request","level":"INFO","line":2734,"method":"GET","msg":"request","params":{},"path":"/health","remote_addr":"127.0.0.1","remote_port":56082,"status":200,"tid":"139637473294080","timestamp":1714977496} {"function":"process_single_task","level":"INFO","line":1506,"msg":"slot data","n_idle_slots":1,"n_processing_slots":0,"task_id":42755,"tid":"139643039125504","timestamp":1714977496} {"function":"log_server_request","level":"INFO","line":2734,"method":"GET","msg":"request","params":{},"path":"/health","remote_addr":"127.0.0.1","remote_port":56082,"status":200,"tid":"139637473294080","timestamp":1714977496} {"function":"log_server_request","level":"INFO","line":2734,"method":"POST","msg":"request","params":{},"path":"/tokenize","remote_addr":"127.0.0.1","remote_port":56082,"status":200,"tid":"139637473294080","timestamp":1714977496} {"function":"process_single_task","level":"INFO","line":1506,"msg":"slot data","n_idle_slots":1,"n_processing_slots":0,"task_id":42756,"tid":"139643039125504","timestamp":1714977496} {"function":"log_server_request","level":"INFO","line":2734,"method":"GET","msg":"request","params":{},"path":"/health","remote_addr":"127.0.0.1","remote_port":56082,"status":200,"tid":"139637473294080","timestamp":1714977496} {"function":"launch_slot_with_data","level":"INFO","line":830,"msg":"slot is processing ta…