Re:AMD Funded a Drop-In CUDA Implementation Built on ROCm: I...
by chem83 on Monday February 12, 2024 @12:11PM
(#39347433)
To be fair to AMD, they've been trying to solve ML workload portability at more fundamental levels with the acquisition of Nod.ai and de-facto incorporation of Google's IREE compiler project + MLIR.
[ Parent
| on HN ]
There are no comments on this comment yet.