char-fork/llama.cpp

git clone https://git.t4t.associates/char-fork/llama.cpp

Charlotte Somenc/dec in server context8300f1411

char/aliceai-t5-moe
brancheschar/aliceai-t5-moeall refs →
80 files

files

CMakeLists.txt1.2 KiB
act-ops.c32.9 KiB
allreduce-ops.c35.9 KiB
allreduce-ops.h1.1 KiB
argsort-ops.c21.3 KiB
binary-ops.c43.9 KiB
cmake-toolchain.cmake5.4 KiB
concat-ops.c13.1 KiB
cpy-ops.c22.0 KiB
cumsum-ops.c11.3 KiB
diag-ops.c9.7 KiB
dma-queue.c2.7 KiB
dma-queue.h11.6 KiB
fill-ops.c4.9 KiB
flash-attn-ops.c118.5 KiB
flash-attn-ops.h14.5 KiB
gated-delta-net-ops.c58.4 KiB
get-rows-ops.c21.7 KiB
get-rows-ops.h2.2 KiB
hex-bitmap.h634 B
hex-common.h1.9 KiB
hex-dma.h36 B
hex-dump.h2.6 KiB
hex-fastdiv.h1.1 KiB
hex-profile.h2.0 KiB
hex-utils.h2.0 KiB
hmx-fa-kernels.h22.1 KiB
hmx-mm-kernels-tiled.h63.5 KiB
hmx-queue.c4.8 KiB
hmx-queue.h4.1 KiB
hmx-utils.h10.8 KiB
htp-ctx.h5.3 KiB
htp-fence.h3.2 KiB
htp-ops.h7.1 KiB
htp-tensor.c11.8 KiB
htp-tensor.h4.5 KiB
htp-vtcm.h684 B
htp_iface.idl675 B
hvx-arith.h41.2 KiB
hvx-base.h10.1 KiB
hvx-copy.h14.0 KiB
hvx-div.h21.5 KiB
hvx-dump.h3.1 KiB
hvx-exp.h9.8 KiB
hvx-fa-kernels.h11.1 KiB
hvx-flash-attn.h1.8 KiB
hvx-floor.h3.9 KiB
hvx-inverse.h11.7 KiB
hvx-log.h3.9 KiB
hvx-mm-kernels-flat.h70.0 KiB
hvx-mm-kernels-tiled.h53.9 KiB
hvx-norm.h19.4 KiB
hvx-pow.h1.4 KiB
hvx-quant.h6.5 KiB
hvx-reduce.h13.7 KiB
hvx-repl.h4.5 KiB
hvx-scale.h12.2 KiB
hvx-sigmoid.h9.0 KiB
hvx-sin-cos.h3.5 KiB
hvx-sqrt.h8.7 KiB
hvx-types.h700 B
hvx-utils.h476 B
im2col-ops.c23.5 KiB
main.c41.6 KiB
matmul-ops.c218.3 KiB
matmul-ops.h31.8 KiB
pad-ops.c24.2 KiB
repeat-ops.c5.6 KiB
rope-ops.c34.1 KiB
rope-ops.h1.8 KiB
set-rows-ops.c18.2 KiB
set-rows-ops.h2.1 KiB
softmax-ops.c16.1 KiB
solve-tri-ops.c11.6 KiB
ssm-conv.c18.8 KiB
sum-rows-ops.c5.3 KiB
unary-ops.c79.9 KiB
unary-ops.h5.9 KiB
work-queue.c7.8 KiB
work-queue.h1.2 KiB