Johannes Gäßler 1613ef8d8e CUDA: CUDART < 11.7 workaround for __hmax, __hmax2 (#7019)		2024-05-01 14:46:37 +02:00
..
acc.cu
acc.cuh
alibi.cu
alibi.cuh
arange.cu
arange.cuh
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
binbcast.cu	ggml : group all experts in a single ggml_mul_mat_id (#6505)	2024-04-18 15:18:48 +02:00
binbcast.cuh
clamp.cu
clamp.cuh
common.cuh	CUDA: CUDART < 11.7 workaround for __hmax, __hmax2 (#7019)	2024-05-01 14:46:37 +02:00
concat.cu
concat.cuh
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
cpy.cuh
dequantize.cuh	llama : add Command R Plus support (#6491)	2024-04-09 11:16:13 +03:00
diagmask.cu
diagmask.cuh
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
getrows.cuh
im2col.cu
im2col.cuh
mmq.cu
mmq.cuh
mmvq.cu	IQ1_M: 1.75 bpw quantization (#6302)	2024-03-26 15:21:27 +01:00
mmvq.cuh
norm.cu
norm.cuh
pad.cu
pad.cuh
pool2d.cu
pool2d.cuh
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
rope.cuh
scale.cu
scale.cuh
softmax.cu	ggml : add Flash Attention (#5021)	2024-04-30 12:16:08 +03:00
softmax.cuh
sumrows.cu
sumrows.cuh
tsembd.cu
tsembd.cuh
unary.cu
unary.cuh
upscale.cu
upscale.cuh
vecdotq.cuh	IQ1_M: 1.75 bpw quantization (#6302)	2024-03-26 15:21:27 +01:00