| .. |
|
amx
|
70680c48e5
ggml : upgrade init_tensor API to return a ggml_status (#11854)
|
11 months ago |
|
cmake
|
ae8de6d50a
ggml : build backends as libraries (#10256)
|
1 year ago |
|
kleidiai
|
053b3f9aae
ggml-cpu : update KleidiAI to v1.5.0 (#12568)
|
10 months ago |
|
llamafile
|
13731766db
llamafile : ppc64le GEMV forwarding for FP32. (#12594)
|
10 months ago |
|
CMakeLists.txt
|
44cd8d91ff
feat(ggml-cpu): enable z17 compile (#13182)
|
9 months ago |
|
binary-ops.cpp
|
a62d7fa7a9
cpu: de-duplicate some of the operators and refactor (ggml/1144)
|
10 months ago |
|
binary-ops.h
|
a62d7fa7a9
cpu: de-duplicate some of the operators and refactor (ggml/1144)
|
10 months ago |
|
common.h
|
a62d7fa7a9
cpu: de-duplicate some of the operators and refactor (ggml/1144)
|
10 months ago |
|
cpu-feats-x86.cpp
|
1d735c0b4f
ggml : add SSE 4.2 and x64 base variant for CPUs without AVX (#12871)
|
9 months ago |
|
ggml-cpu-aarch64.cpp
|
eccc7a1602
ggml : Add AVX512 implementation of GEMM - Q4_Kx8 (#12829)
|
9 months ago |
|
ggml-cpu-aarch64.h
|
19d8762ab6
ggml : refactor online repacking (#10446)
|
1 year ago |
|
ggml-cpu-hbm.cpp
|
19d8762ab6
ggml : refactor online repacking (#10446)
|
1 year ago |
|
ggml-cpu-hbm.h
|
19d8762ab6
ggml : refactor online repacking (#10446)
|
1 year ago |
|
ggml-cpu-impl.h
|
31f7803bc4
ggml-cpu-impl.h: do not redefine bool on POWER9 (#12856)
|
9 months ago |
|
ggml-cpu-quants.c
|
24feaec057
ggml : riscv: add 128-bit RVV support (#12530)
|
10 months ago |
|
ggml-cpu-quants.h
|
ae8de6d50a
ggml : build backends as libraries (#10256)
|
1 year ago |
|
ggml-cpu-traits.cpp
|
19d8762ab6
ggml : refactor online repacking (#10446)
|
1 year ago |
|
ggml-cpu-traits.h
|
19d8762ab6
ggml : refactor online repacking (#10446)
|
1 year ago |
|
ggml-cpu.c
|
77d5e9a76a
ggml: move fp16/bf16 conversion optimizations to CPU backend + export conversion APIs (#13107)
|
9 months ago |
|
ggml-cpu.cpp
|
a25355e264
cpu: fix cpu backend's supports-op for GET_ROWS_BACK. fixes a fatal when running test-backend-ops with only the CPU backend (ggml/1190)
|
9 months ago |
|
ops.cpp
|
77d5e9a76a
ggml: move fp16/bf16 conversion optimizations to CPU backend + export conversion APIs (#13107)
|
9 months ago |
|
ops.h
|
c6e8cc28c1
ggml : Depthwise 2D convolution (ggml/1152)
|
9 months ago |
|
simd-mappings.h
|
416313773b
ggml : fix ppc64le build (#13176)
|
9 months ago |
|
unary-ops.cpp
|
a62d7fa7a9
cpu: de-duplicate some of the operators and refactor (ggml/1144)
|
10 months ago |
|
unary-ops.h
|
a62d7fa7a9
cpu: de-duplicate some of the operators and refactor (ggml/1144)
|
10 months ago |
|
vec.cpp
|
995083e4ed
cpu: move all the operators into a separate c++ file (except mul_mat) (ggml/1167)
|
9 months ago |
|
vec.h
|
995083e4ed
cpu: move all the operators into a separate c++ file (except mul_mat) (ggml/1167)
|
9 months ago |
shalinib-ibm
416313773b
ggml : fix ppc64le build (#13176)