Home Verkennen Help
Registreren Inloggen
david
/
flash-attention
spiegel van https://github.com/Dao-AILab/flash-attention
1
0
Vork 0
Bestanden Issues 0 Wiki
Boom: 9b6cba16c1
Aftakkingen Labels
flash-attention
/
csrc
/
fused_softmax
Chirag Jain 50896ec574 Make nvcc threads configurable via environment variable (#885) 9 maanden geleden
..
fused_softmax.cpp ed553e9238 Add Megatron attention implementation for benchmarking 2 jaren geleden
scaled_masked_softmax.h ed553e9238 Add Megatron attention implementation for benchmarking 2 jaren geleden
scaled_masked_softmax_cuda.cu ed553e9238 Add Megatron attention implementation for benchmarking 2 jaren geleden
scaled_upper_triang_masked_softmax.h ed553e9238 Add Megatron attention implementation for benchmarking 2 jaren geleden
scaled_upper_triang_masked_softmax_cuda.cu ed553e9238 Add Megatron attention implementation for benchmarking 2 jaren geleden
setup.py 50896ec574 Make nvcc threads configurable via environment variable (#885) 9 maanden geleden
type_shim.h ed553e9238 Add Megatron attention implementation for benchmarking 2 jaren geleden