Tri Dao 4ead9bd7cc [FA3] Varlen forward 4 月之前
..
__init__.py 7f67966cc7 FA3 initial code release 5 月之前
block_info.h 7f67966cc7 FA3 initial code release 5 月之前
epilogue_fwd_sm90_tma.hpp 4ead9bd7cc [FA3] Varlen forward 4 月之前
flash.h 4ead9bd7cc [FA3] Varlen forward 4 月之前
flash_api.cpp 4ead9bd7cc [FA3] Varlen forward 4 月之前
flash_attn_interface.py 4ead9bd7cc [FA3] Varlen forward 4 月之前
flash_bwd_hdim128_fp16_sm90.cu 7f67966cc7 FA3 initial code release 5 月之前
flash_bwd_hdim256_fp16_sm90.cu 7f67966cc7 FA3 initial code release 5 月之前
flash_bwd_hdim64_fp16_sm90.cu 7f67966cc7 FA3 initial code release 5 月之前
flash_bwd_kernel.h 7f67966cc7 FA3 initial code release 5 月之前
flash_bwd_launch_template.h 7f67966cc7 FA3 initial code release 5 月之前
flash_bwd_preprocess_kernel.h 7f67966cc7 FA3 initial code release 5 月之前
flash_fwd_hdim128_bf16_sm90.cu 74b0761ff7 [FA3] BF16 forward 5 月之前
flash_fwd_hdim128_fp16_sm90.cu 7f67966cc7 FA3 initial code release 5 月之前
flash_fwd_hdim256_bf16_sm90.cu 74b0761ff7 [FA3] BF16 forward 5 月之前
flash_fwd_hdim256_fp16_sm90.cu 7f67966cc7 FA3 initial code release 5 月之前
flash_fwd_hdim64_bf16_sm90.cu 74b0761ff7 [FA3] BF16 forward 5 月之前
flash_fwd_hdim64_fp16_sm90.cu 7f67966cc7 FA3 initial code release 5 月之前
flash_fwd_kernel.h 4ead9bd7cc [FA3] Varlen forward 4 月之前
flash_fwd_launch_template.h 4ead9bd7cc [FA3] Varlen forward 4 月之前
kernel_traits.h 7f67966cc7 FA3 initial code release 5 月之前
mainloop_fwd_sm90_tma_gmma_ws.hpp 4ead9bd7cc [FA3] Varlen forward 4 月之前
named_barrier.hpp 74b0761ff7 [FA3] BF16 forward 5 月之前
setup.py 74b0761ff7 [FA3] BF16 forward 5 月之前
softmax.h 7f67966cc7 FA3 initial code release 5 月之前
static_switch.h 7f67966cc7 FA3 initial code release 5 月之前
test_flash_attn.py 4ead9bd7cc [FA3] Varlen forward 4 月之前
tile_scheduler.hpp 4ead9bd7cc [FA3] Varlen forward 4 月之前
utils.h 7f67966cc7 FA3 initial code release 5 月之前