Alternatively to EXLA/Torchx, any thoughts on supporting an ML compiler frontend like Google IREE/MLIR by generating StableHLO or LinAlg? This could pave the way towards supporting multiple hardware targets (Vulkan-based, RVV-based, SME-based etc.) with minimal effort from the framework.
Alternatively to EXLA/Torchx, any thoughts on supporting an ML compiler frontend like Google IREE/MLIR by generating StableHLO or LinAlg? This could pave the way towards supporting multiple hardware targets (Vulkan-based, RVV-based, SME-based etc.) with minimal effort from the framework.