|
Up
|
|
|
|
|
template-instances/
|
— |
|
|
|
vendors/
|
— |
|
|
|
acc.cu
|
|
|
|
|
acc.cuh
|
|
|
|
|
add-id.cu
|
|
|
|
|
add-id.cuh
|
|
|
|
|
arange.cu
|
|
|
|
|
arange.cuh
|
|
|
|
|
argmax.cu
|
|
|
|
|
argmax.cuh
|
|
|
|
|
argsort.cu
|
|
|
|
|
argsort.cuh
|
|
|
|
|
binbcast.cu
|
|
|
|
|
binbcast.cuh
|
|
|
|
|
clamp.cu
|
|
|
|
|
clamp.cuh
|
|
|
|
|
CMakeLists.txt
|
|
|
|
|
common.cuh
|
|
|
|
|
concat.cu
|
|
|
|
|
concat.cuh
|
|
|
|
|
conv-transpose-1d.cu
|
|
|
|
|
conv-transpose-1d.cuh
|
|
|
|
|
conv2d-dw.cu
|
|
|
|
|
conv2d-dw.cuh
|
|
|
|
|
conv2d-transpose.cu
|
|
|
|
|
conv2d-transpose.cuh
|
|
|
|
|
conv2d.cu
|
|
|
|
|
conv2d.cuh
|
|
|
|
|
convert.cu
|
|
|
|
|
convert.cuh
|
|
|
|
|
count-equal.cu
|
|
|
|
|
count-equal.cuh
|
|
|
|
|
cp-async.cuh
|
|
|
|
|
cpy-utils.cuh
|
|
|
|
|
cpy.cu
|
|
|
|
|
cpy.cuh
|
|
|
|
|
cross-entropy-loss.cu
|
|
|
|
|
cross-entropy-loss.cuh
|
|
|
|
|
cumsum.cu
|
|
|
|
|
cumsum.cuh
|
|
|
|
|
dequantize.cuh
|
|
|
|
|
diag.cu
|
|
|
|
|
diag.cuh
|
|
|
|
|
diagmask.cu
|
|
|
|
|
diagmask.cuh
|
|
|
|
|
fattn-common.cuh
|
|
|
|
|
fattn-mma-f16.cuh
|
|
|
|
|
fattn-tile.cu
|
|
|
|
|
fattn-tile.cuh
|
|
|
|
|
fattn-vec.cuh
|
|
|
|
|
fattn-wmma-f16.cu
|
|
|
|
|
fattn-wmma-f16.cuh
|
|
|
|
|
fattn.cu
|
|
|
|
|
fattn.cuh
|
|
|
|
|
fill.cu
|
|
|
|
|
fill.cuh
|
|
|
|
|
gated_delta_net.cu
|
|
|
|
|
gated_delta_net.cuh
|
|
|
|
|
getrows.cu
|
|
|
|
|
getrows.cuh
|
|
|
|
|
ggml-cuda.cu
|
|
|
|
|
gla.cu
|
|
|
|
|
gla.cuh
|
|
|
|
|
im2col.cu
|
|
|
|
|
im2col.cuh
|
|
|
|
|
mean.cu
|
|
|
|
|
mean.cuh
|
|
|
|
|
mma.cuh
|
|
|
|
|
mmf.cu
|
|
|
|
|
mmf.cuh
|
|
|
|
|
mmid.cu
|
|
|
|
|
mmid.cuh
|
|
|
|
|
mmq.cu
|
|
|
|
|
mmq.cuh
|
|
|
|
|
mmvf.cu
|
|
|
|
|
mmvf.cuh
|
|
|
|
|
mmvq.cu
|
|
|
|
|
mmvq.cuh
|
|
|
|
|
norm.cu
|
|
|
|
|
norm.cuh
|
|
|
|
|
opt-step-adamw.cu
|
|
|
|
|
opt-step-adamw.cuh
|
|
|
|
|
opt-step-sgd.cu
|
|
|
|
|
opt-step-sgd.cuh
|
|
|
|
|
out-prod.cu
|
|
|
|
|
out-prod.cuh
|
|
|
|
|
pad.cu
|
|
|
|
|
pad.cuh
|
|
|
|
|
pad_reflect_1d.cu
|
|
|
|
|
pad_reflect_1d.cuh
|
|
|
|
|
pool2d.cu
|
|
|
|
|
pool2d.cuh
|
|
|
|
|
quantize.cu
|
|
|
|
|
quantize.cuh
|
|
|
|
|
reduce_rows.cuh
|
|
|
|
|
roll.cu
|
|
|
|
|
roll.cuh
|
|
|
|
|
rope.cu
|
|
|
|
|
rope.cuh
|
|
|
|
|
scale.cu
|
|
|
|
|
scale.cuh
|
|
|
|
|
set-rows.cu
|
|
|
|
|
set-rows.cuh
|
|
|
|
|
set.cu
|
|
|
|
|
set.cuh
|
|
|
|
|
softcap.cu
|
|
|
|
|
softcap.cuh
|
|
|
|
|
softmax.cu
|
|
|
|
|
softmax.cuh
|
|
|
|
|
solve_tri.cu
|
|
|
|
|
solve_tri.cuh
|
|
|
|
|
ssm-conv.cu
|
|
|
|
|
ssm-conv.cuh
|
|
|
|
|
ssm-scan.cu
|
|
|
|
|
ssm-scan.cuh
|
|
|
|
|
sum.cu
|
|
|
|
|
sum.cuh
|
|
|
|
|
sumrows.cu
|
|
|
|
|
sumrows.cuh
|
|
|
|
|
top-k.cu
|
|
|
|
|
top-k.cuh
|
|
|
|
|
topk-moe.cu
|
|
|
|
|
topk-moe.cuh
|
|
|
|
|
tri.cu
|
|
|
|
|
tri.cuh
|
|
|
|
|
tsembd.cu
|
|
|
|
|
tsembd.cuh
|
|
|
|
|
unary.cu
|
|
|
|
|
unary.cuh
|
|
|
|
|
upscale.cu
|
|
|
|
|
upscale.cuh
|
|
|
|
|
vecdotq.cuh
|
|
|
|
|
wkv.cu
|
|
|
|
|
wkv.cuh
|
|
|
|