kforge
Autonomous kernel generation for PyTorch
Speed up your training and inference workloads without leaving PyTorch. kforge supports multiple backends, such as CUDA, ROCm, and Metal.
kforge's CLI can generate optimized kernels for PyTorch
kforge supports the following hardware platforms.
kforge is produced by the team at gimletlabs.ai .
If you are interested in working with us, check out open positions at gimletlabs.ai/join_us