New Features:

- Added support for CUDA 10.1. For more information on CUDA 10.1, refer to the CUDA Toolkit 10 Release Notes
- Added support for NVIDIA Tesla V100 32GB-H (V100-SXM3-32GB-H).
- Added support for NVIDIA HGX-2 server platform.
- NVML Updates: Added a new API nvmlDeviceGetFanSpeed_v2 to retrieve the intended operating speed of the device's specified fan.
- Added SMBPBI support to read total GPU context and SM utilization on Tesla T4.

Fixed Issues:

- Various security issues were addressed, for additional details on the med-high severity issues please review NVIDIA Product Security for more information.
- Fixed an issue where nvidia-persistenced.service was incorrectly configured on POWER systems with Ubuntu 18.04.
- Fixed a performance issue with reading metrics from CUPTI in continuous mode.
- Fixed an issue in NVML where systems with more than 8 Mellanox devices would result in incorrect topology reported by nvidia-smi.
- Added support in NVML for Turing TU104 based products - Tesla T4, Quadro RTX 4000, Quadro RTX 5000.
- Fixed an issue in NVML where systems with more than 8 Mellanox devices would result in incorrect topology reported by nvidia-smi.

Known Issues:

- NVML: NVML APIs may report incorrect values for NVLink counters (read/write). This issue will be fixed in a later release of the driver.
- NoScanout Mode: NoScanout mode is no longer supported on NVIDIA Tesla products. If NoScanout mode was previously used, then the following line in the “screen” section of /etc/X11/xorg.conf should be removed to ensure that X server starts on Tesla products: Option "UseDisplayDevice" "None". Tesla products now support one display of up to 4K resolution.
- Unified Memory Support: Some Unified Memory APIs (for example, CPU page faults) are not supported on Windows in this version of the driver. Review the CUDA Programming Guide on the system requirements for Unified Memory. CUDA and unified memory is not supported when used with Linux power management states S3/S4.
- IMPU FRU for Volta GPUs: The driver does not support the IPMI FRU multi-record information structure for NVLink. See the Design Guide for Tesla P100 and Tesla V100-SXM2 for more information.
- Video Memory Support: For Windows 7 64-bit, this driver recognizes up to the total available video memory on Tesla cards for Direct3D and OpenGL applications. For Windows 7 32-bit, this driver recognizes only up to 4 GB of video memory on Tesla cards for DirectX, OpenGL, and CUDA applications.
- Experimental OpenCL Features: Select features in OpenCL 2.0 are available in the driver for evaluation purposes only.
- Device side enqueue: The current implementation is limited to 64-bit platforms only.
- Device side enqueue: OpenCL 2.0 allows kernels to be enqueued with global_work_size larger than the compute capability of the NVIDIA GPU. The current implementation supports only combinations of global_work_size and local_work_size that are within the compute capability of the NVIDIA GPU. For a given grid dimension, the global_work_size can be determined by CUDA grid size x CUDA block size.
- Device side enqueue: For executing kernels (whether from the host or the device), OpenCL 2.0 supports non-uniform ND-ranges where global_work_size does not need to be divisible by the local_work_size. This capability is not yet supported in the NVIDIA driver, and therefore not supported for device side kernel enqueues.
- Shared virtual memory: The current implementation of shared virtual memory is limited to 64-bit platforms only.

This release supports the following APIs:

- NVIDIA CUDA 10.1 for NVIDIA Kepler, Maxwell, Pascal, Volta and Turing GPUs
- OpenGL 4.5
- Vulkan 1.1
- DirectX 11
- DirectX 12 (Windows 10)
- Open Computing Language (OpenCL software) 1.2

Compatible T-Series:

- Tesla T4

Compatible V-Series:

- Tesla V100

Compatible P-Series:

- Tesla P100, Tesla P40, Tesla P4

Compatible K-Series:

- Tesla K80, Tesla K520, Tesla K40c, Tesla K40m, Tesla K40s, Tesla K40st, Tesla K40t, Tesla K20Xm, Tesla K20m, Tesla K20s, Tesla K20c, Tesla K10, Tesla K8

Compatible M-Class:

- M60, M40 24GB, M40, M6, M4

To install this package please do the following:

- Make sure that all system requirements are met.
- Save the downloadable package on an accessible location (such as your desktop).
- Locate and double-click on the newly-downloaded file.
- Allow Windows to run the file (if necessary).
- Read EULA (End User License Agreement) and agree to proceed with the installation process.
- Follow the on-screen instructions.
- Close the wizard and perform a system reboot to allow changes to take effect.

About Graphics Drivers:

While installing the graphics driver allows the system to properly recognize the chipset and the card manufacturer, updating the video driver can bring about various changes.

It can improve the overall graphics experience and performance in either games or various engineering software applications, include support for newly developed technologies, add compatibility with newer GPU chipsets, or resolve different problems that might have been encountered.

When it comes to applying this release, the installation steps should be a breeze, as each manufacturer tries to make them as easy as possible so that each user can update the GPU on their own and with minimum risks (however, check to see if this download supports your graphics chipset).

Therefore, get the package (extract it if necessary), run the setup, follow the on-screen instructions for a complete and successful installation, and make sure you reboot the system so that the changes take effect.

That being said, download the driver, apply it on your system, and enjoy your newly updated graphics card. Moreover, check with our website as often as possible in order to stay up to speed with the latest releases.