| .. |
|
composable_kernel @ 888317e698
|
77ad12d24e
[AMD ROCm] Support variable length of page attention (#1431)
|
vor 4 Wochen |
|
cutlass @ c506e16788
|
68bf390920
Update Cutlass to fix mem fence
|
vor 1 Monat |
|
flash_attn
|
bc482cbf91
Add a macro for namespace (#1419)
|
vor 3 Wochen |
|
flash_attn_ck
|
74aed78373
Replace c10::optional with std::optional in flash_attn
|
vor 3 Wochen |
|
ft_attention
|
74aed78373
Replace c10::optional with std::optional in flash_attn
|
vor 3 Wochen |
|
fused_dense_lib
|
74aed78373
Replace c10::optional with std::optional in flash_attn
|
vor 3 Wochen |
|
fused_softmax
|
50896ec574
Make nvcc threads configurable via environment variable (#885)
|
vor 11 Monaten |
|
layer_norm
|
74aed78373
Replace c10::optional with std::optional in flash_attn
|
vor 3 Wochen |
|
rotary
|
1feb711f46
Fix compilation with clang on ARM64 (#1285)
|
vor 2 Monaten |
|
xentropy
|
1feb711f46
Fix compilation with clang on ARM64 (#1285)
|
vor 2 Monaten |
Driss Guessous
bc482cbf91
Add a macro for namespace (#1419)