I don't know about tinygrad. But Keras with JAX is typically 30% faster than PyTorch, sometimes more. Our SegmentAnything implementation is 5x faster than the original PyTorch version.
Keras with JAX outperforms PyTorch in speed benchmarks
By
–
By
–
I don't know about tinygrad. But Keras with JAX is typically 30% faster than PyTorch, sometimes more. Our SegmentAnything implementation is 5x faster than the original PyTorch version.