flash-attention/csrc
dan_the_3rd c3f2a632aa
[ft_attention] Fix for seqlen=8136 (#488)
When seqlen=8136, `smem_sz = 48840`, and apparently starting the kernel returns an `invalid argument` CUDA error.

`48840 < 48 * 1024` but apparently it's still above the limit somehow..?
Tested on A100
2023-08-28 10:00:22 -07:00
..
cutlass@3a8f57a3c8 Update Cutlass to v3.2.0 2023-08-27 23:47:28 -07:00
flash_attn Change causal mask to be aligned to bottom-right instead of top-left 2023-08-24 23:41:07 -07:00
ft_attention [ft_attention] Fix for seqlen=8136 (#488) 2023-08-28 10:00:22 -07:00
fused_dense_lib [FusedDense] Allocate lt_workspace on input device 2023-05-30 14:17:26 -07:00
fused_softmax Add Megatron attention implementation for benchmarking 2022-10-23 23:04:16 -07:00
layer_norm Fix random state for dropout_layer_norm (#315) 2023-07-23 15:05:13 -07:00
rotary Support H100 for other CUDA extensions 2023-03-15 16:59:27 -07:00
xentropy Support H100 for other CUDA extensions 2023-03-15 16:59:27 -07:00