| .. |
|
fused_softmax.cpp
|
ed553e9238
Add Megatron attention implementation for benchmarking
|
2 years ago |
|
scaled_masked_softmax.h
|
ed553e9238
Add Megatron attention implementation for benchmarking
|
2 years ago |
|
scaled_masked_softmax_cuda.cu
|
ed553e9238
Add Megatron attention implementation for benchmarking
|
2 years ago |
|
scaled_upper_triang_masked_softmax.h
|
ed553e9238
Add Megatron attention implementation for benchmarking
|
2 years ago |
|
scaled_upper_triang_masked_softmax_cuda.cu
|
ed553e9238
Add Megatron attention implementation for benchmarking
|
2 years ago |
|
setup.py
|
50896ec574
Make nvcc threads configurable via environment variable (#885)
|
9 months ago |
|
type_shim.h
|
ed553e9238
Add Megatron attention implementation for benchmarking
|
2 years ago |
Chirag Jain
50896ec574
Make nvcc threads configurable via environment variable (#885)