flash-attention/flash_attn/ops/triton
Curtis "Fjord" Hawthorne d8aacc510c
return z_loss (#768)
2024-01-21 15:23:41 -08:00
..
__init__.py Create __init__.py for ops/triton dir (#516) 2023-09-05 11:29:03 -07:00
cross_entropy.py return z_loss (#768) 2024-01-21 15:23:41 -08:00
k_activations.py Run isort and black on python files 2023-08-18 14:22:11 -07:00
layer_norm.py [LayerNorm] Initialize mean and rstd tensor using x.device 2024-01-09 16:30:31 -08:00
linear.py [Rotary] Implement rotary in Triton 2023-09-03 02:51:58 -07:00
mlp.py Run isort and black on python files 2023-08-18 14:22:11 -07:00
rotary.py [Gen] Fix calling update_graph_cache in tests 2023-09-10 17:22:37 -07:00