| .. |
|
template-instances
|
CUDA: MMQ for IQ4_KS (#374)
|
2025-05-04 12:45:00 +03:00 |
|
vendors
|
Adding bf16 support to CUDA (#40)
|
2024-09-14 20:02:32 +03:00 |
|
acc.cu
|
Merge mainline llama.cpp (#3)
|
2024-07-27 07:55:01 +02:00 |
|
acc.cuh
|
Merge mainline llama.cpp (#3)
|
2024-07-27 07:55:01 +02:00 |
|
arange.cu
|
Merge mainline llama.cpp (#3)
|
2024-07-27 07:55:01 +02:00 |
|
arange.cuh
|
Merge mainline llama.cpp (#3)
|
2024-07-27 07:55:01 +02:00 |
|
argsort.cu
|
Add copyright notices (#317)
|
2025-04-07 10:43:26 +02:00 |
|
argsort.cuh
|
Add copyright notices (#317)
|
2025-04-07 10:43:26 +02:00 |
|
binbcast.cu
|
Add copyright notices (#317)
|
2025-04-07 10:43:26 +02:00 |
|
binbcast.cuh
|
Merge mainline llama.cpp (#3)
|
2024-07-27 07:55:01 +02:00 |
|
clamp.cu
|
Merge mainline llama.cpp (#3)
|
2024-07-27 07:55:01 +02:00 |
|
clamp.cuh
|
Merge mainline llama.cpp (#3)
|
2024-07-27 07:55:01 +02:00 |
|
common.cuh
|
CUDA: faster FA TG for GQA models (#370)
|
2025-05-04 09:17:44 +03:00 |
|
concat.cu
|
Add copyright notices (#317)
|
2025-04-07 10:43:26 +02:00 |
|
concat.cuh
|
Merge mainline llama.cpp (#3)
|
2024-07-27 07:55:01 +02:00 |
|
conv-transpose-1d.cu
|
Merge mainline llama.cpp (#3)
|
2024-07-27 07:55:01 +02:00 |
|
conv-transpose-1d.cuh
|
Merge mainline llama.cpp (#3)
|
2024-07-27 07:55:01 +02:00 |
|
convert.cu
|
Compile time option to use bf16 for qunts without MMQ kernels (#261)
|
2025-03-18 07:37:10 +01:00 |
|
convert.cuh
|
Add copyright notices (#317)
|
2025-04-07 10:43:26 +02:00 |
|
cp-async.cuh
|
CUDA: faster FA TG for GQA models (#370)
|
2025-05-04 09:17:44 +03:00 |
|
cpy.cu
|
Add copyright notices (#317)
|
2025-04-07 10:43:26 +02:00 |
|
cpy.cuh
|
Merge mainline llama.cpp (#3)
|
2024-07-27 07:55:01 +02:00 |
|
dequantize.cuh
|
Merge mainline llama.cpp (#3)
|
2024-07-27 07:55:01 +02:00 |
|
diagmask.cu
|
Merge mainline llama.cpp (#3)
|
2024-07-27 07:55:01 +02:00 |
|
diagmask.cuh
|
Merge mainline llama.cpp (#3)
|
2024-07-27 07:55:01 +02:00 |
|
dmmv.cu
|
MMQ for Q6_0 (#115)
|
2024-11-21 07:12:11 +01:00 |
|
dmmv.cuh
|
Merge mainline - Aug 12 2024 (#17)
|
2024-08-12 15:14:32 +02:00 |
|
fattn-common.cuh
|
CUDA: faster FA TG for GQA models (#370)
|
2025-05-04 09:17:44 +03:00 |
|
fattn-mma-f16.cuh
|
CUDA: faster FA TG for GQA models (#370)
|
2025-05-04 09:17:44 +03:00 |
|
fattn-new-mma.cu
|
Fix race in the CUDA DeepSeek FA kernel (#406)
|
2025-05-11 08:12:47 +03:00 |
|
fattn-new-mma.cuh
|
FlashMLA-3 for DeepSeek models on CUDA (#386)
|
2025-05-07 17:38:22 +03:00 |
|
fattn-tile-f16.cu
|
Add copyright notices (#317)
|
2025-04-07 10:43:26 +02:00 |
|
fattn-tile-f16.cuh
|
Merge mainline llama.cpp (#3)
|
2024-07-27 07:55:01 +02:00 |
|
fattn-tile-f32.cu
|
Add copyright notices (#317)
|
2025-04-07 10:43:26 +02:00 |
|
fattn-tile-f32.cuh
|
Merge mainline llama.cpp (#3)
|
2024-07-27 07:55:01 +02:00 |
|
fattn-vec-f16.cuh
|
Add copyright notices (#317)
|
2025-04-07 10:43:26 +02:00 |
|
fattn-vec-f32.cuh
|
Add copyright notices (#317)
|
2025-04-07 10:43:26 +02:00 |
|
fattn-wmma-f16.cuh
|
Add copyright notices (#317)
|
2025-04-07 10:43:26 +02:00 |
|
fattn.cu
|
FlashMLA-3 for DeepSeek models on CUDA (#386)
|
2025-05-07 17:38:22 +03:00 |
|
fattn.cuh
|
Merge mainline llama.cpp (#3)
|
2024-07-27 07:55:01 +02:00 |
|
getrows.cu
|
Add copyright notices (#317)
|
2025-04-07 10:43:26 +02:00 |
|
getrows.cuh
|
Merge mainline llama.cpp (#3)
|
2024-07-27 07:55:01 +02:00 |
|
im2col.cu
|
Merge mainline llama.cpp (#3)
|
2024-07-27 07:55:01 +02:00 |
|
im2col.cuh
|
Merge mainline llama.cpp (#3)
|
2024-07-27 07:55:01 +02:00 |
|
iqk_mmvq.cu
|
Faster MoE token generation on CUDA (#248)
|
2025-03-10 16:16:51 +02:00 |
|
iqk_mmvq.cuh
|
Add copyright notices (#317)
|
2025-04-07 10:43:26 +02:00 |
|
mma.cuh
|
Merge mainline llama.cpp (#3)
|
2024-07-27 07:55:01 +02:00 |
|
mma_new.cuh
|
CUDA: faster FA TG for GQA models (#370)
|
2025-05-04 09:17:44 +03:00 |
|
mmq.cu
|
CUDA: MMQ for IQ4_KS (#374)
|
2025-05-04 12:45:00 +03:00 |
|
mmq.cuh
|
CUDA: MMQ for IQ4_KS (#374)
|
2025-05-04 12:45:00 +03:00 |
|
mmvq.cu
|
TG improvements for MoE models (#404)
|
2025-05-10 18:52:54 +03:00 |
|
mmvq.cuh
|
Add copyright notices (#317)
|
2025-04-07 10:43:26 +02:00 |
|
norm.cu
|
cuda: non-contiguous rms norm (#190)
|
2025-02-07 08:33:42 +02:00 |
|
norm.cuh
|
Adding fused rms_norm (#42)
|
2024-09-08 10:19:21 +03:00 |
|
pad.cu
|
Merge mainline llama.cpp (#3)
|
2024-07-27 07:55:01 +02:00 |
|
pad.cuh
|
Merge mainline llama.cpp (#3)
|
2024-07-27 07:55:01 +02:00 |
|
pool2d.cu
|
Merge mainline llama.cpp (#3)
|
2024-07-27 07:55:01 +02:00 |
|
pool2d.cuh
|
Merge mainline llama.cpp (#3)
|
2024-07-27 07:55:01 +02:00 |
|
quantize.cu
|
Add copyright notices (#317)
|
2025-04-07 10:43:26 +02:00 |
|
quantize.cuh
|
Add copyright notices (#317)
|
2025-04-07 10:43:26 +02:00 |
|
rope.cu
|
Add copyright notices (#317)
|
2025-04-07 10:43:26 +02:00 |
|
rope.cuh
|
Merge mainline llama.cpp (#3)
|
2024-07-27 07:55:01 +02:00 |
|
scale.cu
|
Merge mainline llama.cpp (#3)
|
2024-07-27 07:55:01 +02:00 |
|
scale.cuh
|
Merge mainline llama.cpp (#3)
|
2024-07-27 07:55:01 +02:00 |
|
softcap.cu
|
Add copyright notices (#317)
|
2025-04-07 10:43:26 +02:00 |
|
softcap.cuh
|
Add copyright notices (#317)
|
2025-04-07 10:43:26 +02:00 |
|
softmax.cu
|
Add copyright notices (#317)
|
2025-04-07 10:43:26 +02:00 |
|
softmax.cuh
|
Add copyright notices (#317)
|
2025-04-07 10:43:26 +02:00 |
|
sumrows.cu
|
Merge mainline llama.cpp (#3)
|
2024-07-27 07:55:01 +02:00 |
|
sumrows.cuh
|
Merge mainline llama.cpp (#3)
|
2024-07-27 07:55:01 +02:00 |
|
tsembd.cu
|
Merge mainline llama.cpp (#3)
|
2024-07-27 07:55:01 +02:00 |
|
tsembd.cuh
|
Merge mainline llama.cpp (#3)
|
2024-07-27 07:55:01 +02:00 |
|
unary.cu
|
Add copyright notices (#317)
|
2025-04-07 10:43:26 +02:00 |
|
unary.cuh
|
Add copyright notices (#317)
|
2025-04-07 10:43:26 +02:00 |
|
upscale.cu
|
Merge mainline llama.cpp (#3)
|
2024-07-27 07:55:01 +02:00 |
|
upscale.cuh
|
Merge mainline llama.cpp (#3)
|
2024-07-27 07:55:01 +02:00 |
|
vecdotq.cuh
|
CUDA: MMQ for IQ4_KS (#374)
|
2025-05-04 12:45:00 +03:00 |
0abcf0749e