| .. |
|
acc.cu
|
cuda : refactor into multiple files (#6269)
|
2024-03-25 13:50:23 +01:00 |
|
acc.cuh
|
cuda : refactor into multiple files (#6269)
|
2024-03-25 13:50:23 +01:00 |
|
alibi.cu
|
cuda : refactor into multiple files (#6269)
|
2024-03-25 13:50:23 +01:00 |
|
alibi.cuh
|
cuda : refactor into multiple files (#6269)
|
2024-03-25 13:50:23 +01:00 |
|
arange.cu
|
cuda : refactor into multiple files (#6269)
|
2024-03-25 13:50:23 +01:00 |
|
arange.cuh
|
cuda : refactor into multiple files (#6269)
|
2024-03-25 13:50:23 +01:00 |
|
argsort.cu
|
ggml : mul_mat_id use the same tensor for all the experts (#6387)
|
2024-04-03 16:07:05 +03:00 |
|
argsort.cuh
|
cuda : refactor into multiple files (#6269)
|
2024-03-25 13:50:23 +01:00 |
|
binbcast.cu
|
ggml : group all experts in a single ggml_mul_mat_id (#6505)
|
2024-04-18 15:18:48 +02:00 |
|
binbcast.cuh
|
cuda : refactor into multiple files (#6269)
|
2024-03-25 13:50:23 +01:00 |
|
clamp.cu
|
cuda : refactor into multiple files (#6269)
|
2024-03-25 13:50:23 +01:00 |
|
clamp.cuh
|
cuda : refactor into multiple files (#6269)
|
2024-03-25 13:50:23 +01:00 |
|
common.cuh
|
CUDA: CUDART < 11.7 workaround for __hmax, __hmax2 (#7019)
|
2024-05-01 14:46:37 +02:00 |
|
concat.cu
|
cuda : refactor into multiple files (#6269)
|
2024-03-25 13:50:23 +01:00 |
|
concat.cuh
|
cuda : refactor into multiple files (#6269)
|
2024-03-25 13:50:23 +01:00 |
|
convert.cu
|
Fix more int overflow during quant (PPL/CUDA). (#6563)
|
2024-04-29 00:38:44 +02:00 |
|
convert.cuh
|
llama : add Command R Plus support (#6491)
|
2024-04-09 11:16:13 +03:00 |
|
cpy.cu
|
cuda : refactor into multiple files (#6269)
|
2024-03-25 13:50:23 +01:00 |
|
cpy.cuh
|
cuda : refactor into multiple files (#6269)
|
2024-03-25 13:50:23 +01:00 |
|
dequantize.cuh
|
llama : add Command R Plus support (#6491)
|
2024-04-09 11:16:13 +03:00 |
|
diagmask.cu
|
cuda : refactor into multiple files (#6269)
|
2024-03-25 13:50:23 +01:00 |
|
diagmask.cuh
|
cuda : refactor into multiple files (#6269)
|
2024-03-25 13:50:23 +01:00 |
|
dmmv.cu
|
llama : add Command R Plus support (#6491)
|
2024-04-09 11:16:13 +03:00 |
|
dmmv.cuh
|
sync : ggml (#6351)
|
2024-03-29 17:45:46 +02:00 |
|
fattn.cu
|
CUDA: CUDART < 11.7 workaround for __hmax, __hmax2 (#7019)
|
2024-05-01 14:46:37 +02:00 |
|
fattn.cuh
|
ggml : add Flash Attention (#5021)
|
2024-04-30 12:16:08 +03:00 |
|
getrows.cu
|
cuda : refactor into multiple files (#6269)
|
2024-03-25 13:50:23 +01:00 |
|
getrows.cuh
|
cuda : refactor into multiple files (#6269)
|
2024-03-25 13:50:23 +01:00 |
|
im2col.cu
|
cuda : refactor into multiple files (#6269)
|
2024-03-25 13:50:23 +01:00 |
|
im2col.cuh
|
cuda : refactor into multiple files (#6269)
|
2024-03-25 13:50:23 +01:00 |
|
mmq.cu
|
cuda : refactor into multiple files (#6269)
|
2024-03-25 13:50:23 +01:00 |
|
mmq.cuh
|
cuda : refactor into multiple files (#6269)
|
2024-03-25 13:50:23 +01:00 |
|
mmvq.cu
|
IQ1_M: 1.75 bpw quantization (#6302)
|
2024-03-26 15:21:27 +01:00 |
|
mmvq.cuh
|
cuda : refactor into multiple files (#6269)
|
2024-03-25 13:50:23 +01:00 |
|
norm.cu
|
cuda : refactor into multiple files (#6269)
|
2024-03-25 13:50:23 +01:00 |
|
norm.cuh
|
cuda : refactor into multiple files (#6269)
|
2024-03-25 13:50:23 +01:00 |
|
pad.cu
|
cuda : refactor into multiple files (#6269)
|
2024-03-25 13:50:23 +01:00 |
|
pad.cuh
|
cuda : refactor into multiple files (#6269)
|
2024-03-25 13:50:23 +01:00 |
|
pool2d.cu
|
cuda : refactor into multiple files (#6269)
|
2024-03-25 13:50:23 +01:00 |
|
pool2d.cuh
|
cuda : refactor into multiple files (#6269)
|
2024-03-25 13:50:23 +01:00 |
|
quantize.cu
|
llama : add Command R Plus support (#6491)
|
2024-04-09 11:16:13 +03:00 |
|
quantize.cuh
|
llama : add Command R Plus support (#6491)
|
2024-04-09 11:16:13 +03:00 |
|
rope.cu
|
cuda : refactor into multiple files (#6269)
|
2024-03-25 13:50:23 +01:00 |
|
rope.cuh
|
cuda : refactor into multiple files (#6269)
|
2024-03-25 13:50:23 +01:00 |
|
scale.cu
|
cuda : refactor into multiple files (#6269)
|
2024-03-25 13:50:23 +01:00 |
|
scale.cuh
|
cuda : refactor into multiple files (#6269)
|
2024-03-25 13:50:23 +01:00 |
|
softmax.cu
|
ggml : add Flash Attention (#5021)
|
2024-04-30 12:16:08 +03:00 |
|
softmax.cuh
|
cuda : refactor into multiple files (#6269)
|
2024-03-25 13:50:23 +01:00 |
|
sumrows.cu
|
cuda : refactor into multiple files (#6269)
|
2024-03-25 13:50:23 +01:00 |
|
sumrows.cuh
|
cuda : refactor into multiple files (#6269)
|
2024-03-25 13:50:23 +01:00 |
|
tsembd.cu
|
cuda : refactor into multiple files (#6269)
|
2024-03-25 13:50:23 +01:00 |
|
tsembd.cuh
|
cuda : refactor into multiple files (#6269)
|
2024-03-25 13:50:23 +01:00 |
|
unary.cu
|
cuda : refactor into multiple files (#6269)
|
2024-03-25 13:50:23 +01:00 |
|
unary.cuh
|
cuda : refactor into multiple files (#6269)
|
2024-03-25 13:50:23 +01:00 |
|
upscale.cu
|
cuda : refactor into multiple files (#6269)
|
2024-03-25 13:50:23 +01:00 |
|
upscale.cuh
|
cuda : refactor into multiple files (#6269)
|
2024-03-25 13:50:23 +01:00 |
|
vecdotq.cuh
|
IQ1_M: 1.75 bpw quantization (#6302)
|
2024-03-26 15:21:27 +01:00 |
1613ef8d8e