Menu

Port a PyTorch workload to a new accelerator
📰

Port a PyTorch workload to a new accelerator

DEV Community: pytorch·Conor Bronsdon·19 minutes ago
#k3Da94jY
#devtopytorch#devto#dev#model#attention
Reading 0:00
15s threshold

Much of the cost of switching accelerators lives in the software around the model. Memory capacity is the part a roadmap can close; a kernel tuned for one device is the part you may have to redo. I would start with a saved run from the old device and a list of which code may move unchanged.

Which parts of the model should already run?

Anush Elangovan at AMD calls the older experience a port to platform. A model launches, then someone else makes it work. He now points to day-zero support for recent frontier releases, including DeepSeek, Llama, and Qwen, running natively, as well as they do on the competing platform. That confidence is what a buyer is paying NVIDIA for: a model announced in the morning is supposed to run that afternoon.

In a later conversation he treats PyTorch and vLLM as fully enabled, and says AMD can block upstream pull requests that were tested only on NVIDIA so those changes do not regress AMD. I would confirm both claims for the model you actually serve.…

Continue reading — create a free account

Join HashtagPLUS to read full articles, follow hashtags, vote, and join the conversation.