| .. |
|
acc.cu
|
ae1f211ce2
cuda : refactor into multiple files (#6269)
|
1 jaar geleden |
|
acc.cuh
|
ae1f211ce2
cuda : refactor into multiple files (#6269)
|
1 jaar geleden |
|
alibi.cu
|
ae1f211ce2
cuda : refactor into multiple files (#6269)
|
1 jaar geleden |
|
alibi.cuh
|
ae1f211ce2
cuda : refactor into multiple files (#6269)
|
1 jaar geleden |
|
arange.cu
|
ae1f211ce2
cuda : refactor into multiple files (#6269)
|
1 jaar geleden |
|
arange.cuh
|
ae1f211ce2
cuda : refactor into multiple files (#6269)
|
1 jaar geleden |
|
argsort.cu
|
08a0c02060
ggml : mul_mat_id use the same tensor for all the experts (#6387)
|
1 jaar geleden |
|
argsort.cuh
|
ae1f211ce2
cuda : refactor into multiple files (#6269)
|
1 jaar geleden |
|
binbcast.cu
|
0d56246f4b
ggml : group all experts in a single ggml_mul_mat_id (#6505)
|
1 jaar geleden |
|
binbcast.cuh
|
ae1f211ce2
cuda : refactor into multiple files (#6269)
|
1 jaar geleden |
|
clamp.cu
|
ae1f211ce2
cuda : refactor into multiple files (#6269)
|
1 jaar geleden |
|
clamp.cuh
|
ae1f211ce2
cuda : refactor into multiple files (#6269)
|
1 jaar geleden |
|
common.cuh
|
5dc9dd7152
llama : add Command R Plus support (#6491)
|
1 jaar geleden |
|
concat.cu
|
ae1f211ce2
cuda : refactor into multiple files (#6269)
|
1 jaar geleden |
|
concat.cuh
|
ae1f211ce2
cuda : refactor into multiple files (#6269)
|
1 jaar geleden |
|
convert.cu
|
0d56246f4b
ggml : group all experts in a single ggml_mul_mat_id (#6505)
|
1 jaar geleden |
|
convert.cuh
|
5dc9dd7152
llama : add Command R Plus support (#6491)
|
1 jaar geleden |
|
cpy.cu
|
ae1f211ce2
cuda : refactor into multiple files (#6269)
|
1 jaar geleden |
|
cpy.cuh
|
ae1f211ce2
cuda : refactor into multiple files (#6269)
|
1 jaar geleden |
|
dequantize.cuh
|
5dc9dd7152
llama : add Command R Plus support (#6491)
|
1 jaar geleden |
|
diagmask.cu
|
ae1f211ce2
cuda : refactor into multiple files (#6269)
|
1 jaar geleden |
|
diagmask.cuh
|
ae1f211ce2
cuda : refactor into multiple files (#6269)
|
1 jaar geleden |
|
dmmv.cu
|
5dc9dd7152
llama : add Command R Plus support (#6491)
|
1 jaar geleden |
|
dmmv.cuh
|
d48ccf3ad4
sync : ggml (#6351)
|
1 jaar geleden |
|
getrows.cu
|
ae1f211ce2
cuda : refactor into multiple files (#6269)
|
1 jaar geleden |
|
getrows.cuh
|
ae1f211ce2
cuda : refactor into multiple files (#6269)
|
1 jaar geleden |
|
im2col.cu
|
ae1f211ce2
cuda : refactor into multiple files (#6269)
|
1 jaar geleden |
|
im2col.cuh
|
ae1f211ce2
cuda : refactor into multiple files (#6269)
|
1 jaar geleden |
|
mmq.cu
|
ae1f211ce2
cuda : refactor into multiple files (#6269)
|
1 jaar geleden |
|
mmq.cuh
|
ae1f211ce2
cuda : refactor into multiple files (#6269)
|
1 jaar geleden |
|
mmvq.cu
|
55c1b2a3bb
IQ1_M: 1.75 bpw quantization (#6302)
|
1 jaar geleden |
|
mmvq.cuh
|
ae1f211ce2
cuda : refactor into multiple files (#6269)
|
1 jaar geleden |
|
norm.cu
|
ae1f211ce2
cuda : refactor into multiple files (#6269)
|
1 jaar geleden |
|
norm.cuh
|
ae1f211ce2
cuda : refactor into multiple files (#6269)
|
1 jaar geleden |
|
pad.cu
|
ae1f211ce2
cuda : refactor into multiple files (#6269)
|
1 jaar geleden |
|
pad.cuh
|
ae1f211ce2
cuda : refactor into multiple files (#6269)
|
1 jaar geleden |
|
pool2d.cu
|
ae1f211ce2
cuda : refactor into multiple files (#6269)
|
1 jaar geleden |
|
pool2d.cuh
|
ae1f211ce2
cuda : refactor into multiple files (#6269)
|
1 jaar geleden |
|
quantize.cu
|
5dc9dd7152
llama : add Command R Plus support (#6491)
|
1 jaar geleden |
|
quantize.cuh
|
5dc9dd7152
llama : add Command R Plus support (#6491)
|
1 jaar geleden |
|
rope.cu
|
ae1f211ce2
cuda : refactor into multiple files (#6269)
|
1 jaar geleden |
|
rope.cuh
|
ae1f211ce2
cuda : refactor into multiple files (#6269)
|
1 jaar geleden |
|
scale.cu
|
ae1f211ce2
cuda : refactor into multiple files (#6269)
|
1 jaar geleden |
|
scale.cuh
|
ae1f211ce2
cuda : refactor into multiple files (#6269)
|
1 jaar geleden |
|
softmax.cu
|
ae1f211ce2
cuda : refactor into multiple files (#6269)
|
1 jaar geleden |
|
softmax.cuh
|
ae1f211ce2
cuda : refactor into multiple files (#6269)
|
1 jaar geleden |
|
sumrows.cu
|
ae1f211ce2
cuda : refactor into multiple files (#6269)
|
1 jaar geleden |
|
sumrows.cuh
|
ae1f211ce2
cuda : refactor into multiple files (#6269)
|
1 jaar geleden |
|
tsembd.cu
|
ae1f211ce2
cuda : refactor into multiple files (#6269)
|
1 jaar geleden |
|
tsembd.cuh
|
ae1f211ce2
cuda : refactor into multiple files (#6269)
|
1 jaar geleden |
|
unary.cu
|
ae1f211ce2
cuda : refactor into multiple files (#6269)
|
1 jaar geleden |
|
unary.cuh
|
ae1f211ce2
cuda : refactor into multiple files (#6269)
|
1 jaar geleden |
|
upscale.cu
|
ae1f211ce2
cuda : refactor into multiple files (#6269)
|
1 jaar geleden |
|
upscale.cuh
|
ae1f211ce2
cuda : refactor into multiple files (#6269)
|
1 jaar geleden |
|
vecdotq.cuh
|
55c1b2a3bb
IQ1_M: 1.75 bpw quantization (#6302)
|
1 jaar geleden |
slaren
0d56246f4b
ggml : group all experts in a single ggml_mul_mat_id (#6505)