AMD has released an updated ROCm 5.7.1 driver for Ubuntu Linux that adds PyTorch 2.0.1 compatibility for Radeon Pro W7900 and Radeon RX 7900 XTX graphics cards based on RDNA 3. Developers may now use AMD’s flagship client GPUs with 24GB and 48GB of RAM for artificial intelligence applications that use PyTorch libraries.
The driver update is specifically designed to work with PyTorch 2.0.1, a popular deep learning package, bringing AMD’s RDNA3-based GPUs to life. The ROCm 5.7.1 driver only supports the Radeon RX 7900 XTX 24GB and Radeon Pro W7900 48GB graphics cards. This makes sense because AI applications like large language models (LLM) benefit from big amounts of onboard memory, and AMD wants to sell as many high-end boards as possible.
AMD claims that its Navi 31 graphics processor has 192 AI accelerators built in, up from 96 in the Navi 21, making it a viable GPU for AI applications. Meanwhile, AMD’s Radeon RX 7900 XTX 24 GB graphics card has an MSRP of $999, which is a fraction of the cost of professional AI and HPC GPUs.
Here’s what AMD’s associates had to say about the ROCm 5.7.1
“We are excited to offer the AI community new support for machine learning development using PyTorch built on the AMD Radeon RX 7900 XTX and Radeon Pro W7900 GPUs and the ROCm open software platform. This is our first RDNA 3 architecture-based implementation, and we are looking forward to partnering with the community,” says Dan Wood, Corp. Vice President, Radeon Product Management at AMD.
AMD enables a nuanced convergence of gaming and professional GPU functionalities by introducing sophisticated ML support to consumer-grade GPUs, which was previously reserved for professional applications. AMD intends to establish a thriving ecosystem for open-source platforms, paving the door for more cost-efficiency and broader accessibility.
Also Read:
