Inicio Explorar Axuda
Rexistro Iniciar sesión
david
/
flash-attention
réplica de https://github.com/Dao-AILab/flash-attention
1
0
Fork 0
Ficheiros Incidencias 0 Wiki
Árbore: 9b6cba16c1
Ramas Etiquetas
flash-attention
/
csrc
/
fused_softmax
Chirag Jain 50896ec574 Make nvcc threads configurable via environment variable (#885) hai 9 meses
..
fused_softmax.cpp ed553e9238 Add Megatron attention implementation for benchmarking %!s(int64=2) %!d(string=hai) anos
scaled_masked_softmax.h ed553e9238 Add Megatron attention implementation for benchmarking %!s(int64=2) %!d(string=hai) anos
scaled_masked_softmax_cuda.cu ed553e9238 Add Megatron attention implementation for benchmarking %!s(int64=2) %!d(string=hai) anos
scaled_upper_triang_masked_softmax.h ed553e9238 Add Megatron attention implementation for benchmarking %!s(int64=2) %!d(string=hai) anos
scaled_upper_triang_masked_softmax_cuda.cu ed553e9238 Add Megatron attention implementation for benchmarking %!s(int64=2) %!d(string=hai) anos
setup.py 50896ec574 Make nvcc threads configurable via environment variable (#885) hai 9 meses
type_shim.h ed553e9238 Add Megatron attention implementation for benchmarking %!s(int64=2) %!d(string=hai) anos