ggml/src/ggml-cuda - ggml-org/llama.cpp

LLM inference in C/C++

0 0 0 C++

	template-instances
	vendors
	acc.cu	2.4 KB
	acc.cuh	131 B
	add-id.cu	1.9 KB
	add-id.cuh	101 B
	arange.cu	1.2 KB
	arange.cuh	137 B
	argmax.cu	2.8 KB
	argmax.cuh	98 B
	argsort.cu	9.4 KB
	argsort.cuh	868 B
	binbcast.cu	21.4 KB
	binbcast.cuh	579 B
	clamp.cu	1.6 KB
	clamp.cuh	135 B
	CMakeLists.txt	10.6 KB
	common.cuh	52.3 KB
	concat.cu	7.4 KB
	concat.cuh	137 B
	conv-transpose-1d.cu	3.2 KB
	conv-transpose-1d.cuh	158 B
	conv2d-dw.cu	7.2 KB
	conv2d-dw.cuh	155 B
	conv2d-transpose.cu	4.7 KB
	conv2d-transpose.cuh	158 B
	conv2d.cu	6.4 KB
	conv2d.cuh	149 B
	convert.cu	32.7 KB
	convert.cuh	2.3 KB
	count-equal.cu	2.0 KB
	count-equal.cuh	144 B
	cp-async.cuh	2.1 KB
	cpy-utils.cuh	6.2 KB
	cpy.cu	27.6 KB
	cpy.cuh	227 B
	cross-entropy-loss.cu	5.9 KB
	cross-entropy-loss.cuh	251 B
	cumsum.cu	10.7 KB
	cumsum.cuh	137 B
	dequantize.cuh	2.0 KB
	diag.cu	2.6 KB
	diag.cuh	133 B
	diagmask.cu	1.7 KB
	diagmask.cuh	150 B
	fattn-common.cuh	39.1 KB
	fattn-mma-f16.cuh	88.8 KB
	fattn-tile.cu	1.8 KB
	fattn-tile.cuh	57.9 KB
	fattn-vec.cuh	24.0 KB
	fattn-wmma-f16.cu	28.6 KB
	fattn-wmma-f16.cuh	2.0 KB
	fattn.cu	20.4 KB
	fattn.cuh	185 B
	fill.cu	1.1 KB
	fill.cuh	99 B
	gated_delta_net.cu	10.8 KB
	gated_delta_net.cuh	128 B
	getrows.cu	12.5 KB
	getrows.cuh	622 B
	ggml-cuda.cu	213.2 KB
	gla.cu	3.0 KB
	gla.cuh	112 B
	im2col.cu	12.2 KB
	im2col.cuh	218 B
	mean.cu	2.8 KB
	mean.cuh	99 B
	mma.cuh	57.4 KB
	mmf.cu	7.7 KB
	mmf.cuh	44.0 KB
	mmid.cu	7.8 KB
	mmid.cuh	258 B
	mmq.cu	14.2 KB
	mmq.cuh	172.0 KB
	mmvf.cu	39.1 KB
	mmvf.cuh	826 B
	mmvq.cu	54.2 KB
	mmvq.cuh	912 B
	norm.cu	27.7 KB
	norm.cuh	838 B
	opt-step-adamw.cu	2.9 KB
	opt-step-adamw.cuh	150 B
	opt-step-sgd.cu	1.7 KB
	opt-step-sgd.cuh	146 B
	out-prod.cu	2.3 KB
	out-prod.cuh	100 B
	pad_reflect_1d.cu	3.4 KB
	pad_reflect_1d.cuh	153 B
	pad.cu	4.4 KB
	pad.cuh	131 B
	pool2d.cu	3.2 KB
	pool2d.cuh	137 B
	quantize.cu	12.4 KB
	quantize.cuh	1.7 KB
	reduce_rows.cuh	1.1 KB
	roll.cu	2.4 KB
	roll.cuh	133 B
	rope.cu	30.8 KB
	rope.cuh	322 B
	scale.cu	1.4 KB
	scale.cuh	135 B
	set-rows.cu	12.9 KB
	set-rows.cuh	155 B
	set.cu	1.2 KB
	set.cuh	145 B
	softcap.cu	1.3 KB
	softcap.cuh	158 B
	softmax.cu	16.9 KB
	softmax.cuh	228 B
	solve_tri.cu	11.3 KB
	solve_tri.cuh	104 B
	ssm-conv.cu	7.5 KB
	ssm-conv.cuh	137 B
	ssm-scan.cu	16.2 KB
	ssm-scan.cuh	103 B
	sum.cu	1.3 KB
	sum.cuh	210 B
	sumrows.cu	1.8 KB
	sumrows.cuh	212 B
	top-k.cu	4.0 KB
	top-k.cuh	100 B
	topk-moe.cu	16.3 KB
	topk-moe.cuh	1013 B
	tri.cu	5.2 KB
	tri.cuh	131 B
	tsembd.cu	1.8 KB
	tsembd.cuh	161 B
	unary.cu	20.8 KB
	unary.cuh	4.1 KB
	upscale.cu	13.1 KB
	upscale.cuh	139 B
	vecdotq.cuh	44.0 KB
	wkv.cu	6.9 KB
	wkv.cuh	218 B