Failed to initialize NVML: Driver/library version mismatch 的一點解決方案總結。

有時執行nvidia-smi會報錯：

Failed to initialize NVML: Driver/library version mismatch

如果重啓不能解決，此時可通過 sudo dmesg |tail -4 命令確認客戶端和內核驅動版本的差異：

[   27.998032] NVRM: API mismatch: the client has the version 470.182.03, but
               NVRM: this kernel module has the version 470.161.03.  Please
               NVRM: make sure that this kernel module and all NVIDIA driver
               NVRM: components have the same version.

一般地，安裝與客戶端匹配的對應版本號最新版 nvidia 驅動可解決：

sudo apt install nvidia-driver-470

如果 initramfs 報錯導致內核更新失敗，提示如：

dpkg: error processing package initramfs-tools (--configure):
 subprocess installed post-installation script returned error exit status 1
Errors were encountered while processing:
 initramfs-tools

可嘗試重新配置initramfs-tools：

sudo rm -f /var/lib/dpkg/info/initramfs-tools.post*
sudo rm -f /var/lib/dpkg/info/initramfs-tools.pre*
sudo rm -f /var/lib/dpkg/info/bcmwl-kernel-source.post*
sudo rm -f /var/lib/dpkg/info/bcmwl-kernel-source.pre*
sudo dpkg --configure -a

如果由於上述原因導致安裝nvidia-driver-{version}失敗，執行sudo update-initramfs -u時發現/boot分區內存不足：

~$ sudo update-initramfs -u
update-initramfs: Generating /boot/initrd.img-5.15.0-43-generic
Error 24 : Write error : cannot write compressed block
E: mkinitramfs failure cpio 141 lz4 -9 -l 24
update-initramfs: failed for /boot/initrd.img-5.15.0-43-generic with 1.

此時嘗試備份後刪除/boot分區的old內容，重新執行sudo update-initramfs -u即可。

sudo dkms status 可檢查當前狀態。

知識點總結

• dkms：Dynamic Kernel Module Support，動態內核模塊支持。可生成 Linux 內核模塊。
• dmeag：Diagnostic message，診斷信息

參考

• Failed to initialize NVML: Driver/library version mismatch解决
• Nvidia-smi failed to initialize NVML (driver/library version mismatch)