ik_llama_opt/ggml/src/ggml-cuda
Kawrakow 7dcd64c9bd iq2_k: very slightly better CUDA dot product
169.2 t/s vs 167.8 t/s before.
2024-08-01 09:38:06 +02:00
..
template-instances Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
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 Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
argsort.cuh Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
binbcast.cu Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +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 iq5_k: CUDA dot product still not working 2024-08-01 09:38:06 +02:00
concat.cu Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +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 iq5_k: Basics 2024-08-01 09:38:06 +02:00
convert.cuh Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
cpy.cu Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +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 Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
dmmv.cuh Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
fattn-common.cuh Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
fattn-tile-f16.cu Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
fattn-tile-f16.cuh Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
fattn-tile-f32.cu Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
fattn-tile-f32.cuh Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
fattn-vec-f16.cuh Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
fattn-vec-f32.cuh Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
fattn-wmma-f16.cuh Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
fattn.cu Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
fattn.cuh Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
getrows.cu Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +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 iq2_k: very slightly better CUDA dot product 2024-08-01 09:38:06 +02:00
iqk_mmvq.cuh Factor out iqk CUDA dot products 2024-08-01 09:38:06 +02:00
mma.cuh Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
mmq.cu Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
mmq.cuh Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
mmvq.cu Factor out iqk CUDA dot products 2024-08-01 09:38:06 +02:00
mmvq.cuh Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
norm.cu Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
norm.cuh Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
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 Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
quantize.cuh Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
rope.cu Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +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
softmax.cu Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
softmax.cuh Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +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 Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
unary.cuh Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +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 Factor out iqk CUDA dot products 2024-08-01 09:38:06 +02:00