你好，
這個週末我完全重置了我的 NAS，並使用最新的韌體：h6.0.3564 Build 20260723。
在重置之前的安裝過程中，新版 nvkernerdriver 驅動程式已自動安裝。
重置後，Ollama 上無法重新啟動模型；最後在安裝 Nvidia 驅動程式後，重啟後才運作成功。儘管如此，今天早上又再一次無法在 GPU 上啟動模型。
就如同週末時一樣，我在「dmesg」裡看到了這些錯誤：
[59082.857111] NVRM: nvCheckOkFailedNoLog: Check failed: Out of memory [NV_ERR_NO_MEMORY] (0x00000051) returned from _memdescAllocInternal(pMemDesc) @ mem_desc.c:1353
[59082.871729] NVRM: faultbufCtrlCmdMmuFaultBufferRegisterNonReplayBuf_IMPL: Error allocating client shadow fault buffer for non-replayable faults
[59083.013898] NVRM: nvCheckOkFailedNoLog: Check failed: Out of memory [NV_ERR_NO_MEMORY] (0x00000051) returned from _memdescAllocInternal(pMemDesc) @ mem_desc.c:1353
[59083.028519] NVRM: faultbufCtrlCmdMmuFaultBufferRegisterNonReplayBuf_IMPL: Error allocating client shadow fault buffer for non-replayable faults
[59083.568050] NVRM: nvCheckOkFailedNoLog: Check failed: Out of memory [NV_ERR_NO_MEMORY] (0x00000051) returned from _memdescAllocInternal(pMemDesc) @ mem_desc.c:1353
[59083.582684] NVRM: faultbufCtrlCmdMmuFaultBufferRegisterNonReplayBuf_IMPL: Error allocating client shadow fault buffer for non-replayable faults
[59083.638931] NVRM: nvCheckOkFailedNoLog: Check failed: Out of memory [NV_ERR_NO_MEMORY] (0x00000051) returned from _memdescAllocInternal(pMemDesc) @ mem_desc.c:1353
[59083.653570] NVRM: faultbufCtrlCmdMmuFaultBufferRegisterNonReplayBuf_IMPL: Error allocating client shadow fault buffer for non-replayable faults
[59084.839297] NVRM: nvCheckOkFailedNoLog: Check failed: Out of memory [NV_ERR_NO_MEMORY] (0x00000051) returned from _memdescAllocInternal(pMemDesc) @ mem_desc.c:1353
[59084.853921] NVRM: faultbufCtrlCmdMmuFaultBufferRegisterNonReplayBuf_IMPL: Error allocating client shadow fault buffer for non-replayable faults
重新啟動 Ollama 容器並不足以恢復顯示卡功能，我必須重新啟動 NAS。
自從重置後，我終於能夠順利安裝一個虛擬機，虛擬交換器也沒有再出現錯誤。
但這無可否認地造成時間浪費，而備份必須妥善管理。
這週末在研究如何讓顯卡正常運作時，我找到這篇文章；我不是很想按照它的建議去做：Getting GPU-Accelerated PaddlePaddle Working in Docker on QNAP NAS
除非 QNAP 能改善這個情況