Anthony Chang 7c788e10ce Add batched attention special kernel instances (#424) ...

* sanity check

* add attribution

* add irrgular k tile size for batched attention

* format

2022-09-19 19:20:54 -05:00

..

blockwise_gemm_dl_v2r3.hpp

add license in file (#303)

2022-06-24 23:32:43 -05:00

blockwise_gemm_dlops_v2r2.hpp

add license in file (#303)

2022-06-24 23:32:43 -05:00

blockwise_gemm_dlops_v3.hpp

add license in file (#303)

2022-06-24 23:32:43 -05:00

blockwise_gemm_xdlops_skip_b_lds.hpp

Fused GEMM+GEMM (#351)

2022-08-13 09:18:58 -05:00

blockwise_gemm_xdlops.hpp

Add batched attention special kernel instances (#424)

2022-09-19 19:20:54 -05:00

blockwise_softmax.hpp

Fused attention instances & padding tests (#395)

2022-09-06 14:38:56 -05:00

blockwise_tensor_slice_transfer_v5r1.hpp

add license in file (#303)

2022-06-24 23:32:43 -05:00

blockwise_welford.hpp

Layernorm welford (#346)

2022-08-13 09:43:18 -05:00

reduction_functions_blockwise.hpp

Fused attention (#345)

2022-08-13 00:16:14 -05:00

thread_group_tensor_slice_transfer_v4r1.hpp

add license in file (#303)

2022-06-24 23:32:43 -05:00

thread_group_tensor_slice_transfer_v6r1.hpp

add license in file (#303)

2022-06-24 23:32:43 -05:00

thread_group_tensor_slice_transfer_v6r2.hpp

add license in file (#303)

2022-06-24 23:32:43 -05:00

thread_group_tensor_slice_transfer_v6r3.hpp

add license in file (#303)

2022-06-24 23:32:43 -05:00

thread_group_tensor_slice_transfer_v7.hpp

add license in file (#303)

2022-06-24 23:32:43 -05:00