Kernels
relu / OPTIMIZATION.md

Commit History

Align remaining docs with v3 corrections — errata for position-biased L2 ratios, H100 table fix (MK, powered by Claude)
78bf5c2
verified

superexpai commited on

Optimized relu: cpu/cuda/xpu, 1.2-1.85x faster on RTX 4090, benchmarked vs upstream and torch.relu
e873e70
verified

superexpai commited on