| .. |
|
amx
|
60ef23d6c1
ggml-cpu: enable IBM NNPA Vector Intrinsics (#14317)
|
7 months ago |
|
arch
|
d36e61c580
ggml-cpu: clean up s390x SIMD (#15855)
|
4 months ago |
|
cmake
|
ae8de6d50a
ggml : build backends as libraries (#10256)
|
1 year ago |
|
kleidiai
|
2b3efea9a4
kleidiai: fix GGML_ASSERT(*cur_backend_id != -1) failed (#15614)
|
4 months ago |
|
llamafile
|
a6a58d6478
llamafile: PowerPC Sgemm Optimization (#15558)
|
5 months ago |
|
CMakeLists.txt
|
24a6734daf
ggml-cpu : add check for ARM MATMUL_INT8/i8mm support (#15922)
|
4 months ago |
|
arch-fallback.h
|
ad5c975c2d
ggml-cpu: Support Q5_0 and Q5_1 on s390x (#15486)
|
5 months ago |
|
binary-ops.cpp
|
a62d7fa7a9
cpu: de-duplicate some of the operators and refactor (ggml/1144)
|
9 months ago |
|
binary-ops.h
|
a62d7fa7a9
cpu: de-duplicate some of the operators and refactor (ggml/1144)
|
9 months ago |
|
common.h
|
60ef23d6c1
ggml-cpu: enable IBM NNPA Vector Intrinsics (#14317)
|
7 months ago |
|
ggml-cpu-impl.h
|
d36e61c580
ggml-cpu: clean up s390x SIMD (#15855)
|
4 months ago |
|
ggml-cpu.c
|
7ec2df64a4
Added: tri, cumsum. Still a mess.
|
3 months ago |
|
ggml-cpu.cpp
|
e68aa10d8f
vulkan: sort graph to allow more parallel execution (#15850)
|
4 months ago |
|
hbm.cpp
|
f470bc36be
ggml-cpu : split arch-specific implementations (#13892)
|
7 months ago |
|
hbm.h
|
f470bc36be
ggml-cpu : split arch-specific implementations (#13892)
|
7 months ago |
|
ops.cpp
|
666fc0583d
Parity on delta!
|
3 months ago |
|
ops.h
|
7ec2df64a4
Added: tri, cumsum. Still a mess.
|
3 months ago |
|
quants.c
|
fd1234cb46
llama : add gpt-oss (#15091)
|
5 months ago |
|
quants.h
|
fd1234cb46
llama : add gpt-oss (#15091)
|
5 months ago |
|
repack.cpp
|
00f35d509e
ggml : repack block_iq4_nlx8 (#14904)
|
5 months ago |
|
repack.h
|
00f35d509e
ggml : repack block_iq4_nlx8 (#14904)
|
5 months ago |
|
simd-mappings.h
|
186415d595
ggml-cpu: drop support for nnpa intrinsics (#15821)
|
4 months ago |
|
traits.cpp
|
0d8831543c
ggml : fix fallback to CPU for ununsupported ops (#15118)
|
5 months ago |
|
traits.h
|
0d8831543c
ggml : fix fallback to CPU for ununsupported ops (#15118)
|
5 months ago |
|
unary-ops.cpp
|
a62d7fa7a9
cpu: de-duplicate some of the operators and refactor (ggml/1144)
|
9 months ago |
|
unary-ops.h
|
a62d7fa7a9
cpu: de-duplicate some of the operators and refactor (ggml/1144)
|
9 months ago |
|
vec.cpp
|
05c0380f2a
ggml-cpu : optimize RVV kernels (#15720)
|
4 months ago |
|
vec.h
|
7ec2df64a4
Added: tri, cumsum. Still a mess.
|
3 months ago |
Piotr Wilkin
666fc0583d
Parity on delta!