Home Esplora Aiuto
Registrati Accedi
david
/
flash-attention
mirror da https://github.com/Dao-AILab/flash-attention
1
0
Forka 0
File Problemi 0 Wiki
Albero (Tree): 9b6cba16c1
Rami (Branch) Tag
flash-attention
/
csrc
/
fused_softmax
Chirag Jain 50896ec574 Make nvcc threads configurable via environment variable (#885) 9 mesi fa
..
fused_softmax.cpp ed553e9238 Add Megatron attention implementation for benchmarking 2 anni fa
scaled_masked_softmax.h ed553e9238 Add Megatron attention implementation for benchmarking 2 anni fa
scaled_masked_softmax_cuda.cu ed553e9238 Add Megatron attention implementation for benchmarking 2 anni fa
scaled_upper_triang_masked_softmax.h ed553e9238 Add Megatron attention implementation for benchmarking 2 anni fa
scaled_upper_triang_masked_softmax_cuda.cu ed553e9238 Add Megatron attention implementation for benchmarking 2 anni fa
setup.py 50896ec574 Make nvcc threads configurable via environment variable (#885) 9 mesi fa
type_shim.h ed553e9238 Add Megatron attention implementation for benchmarking 2 anni fa