 Jhen-Jie Hong
|
21f3d1be86
k-quants : fix build on armv7 (android only) (#2920)
|
2 years ago |
 Cebtenzzre
|
ef15649972
build : fix most gcc and clang warnings (#2861)
|
2 years ago |
 Ronny Brendel
|
3af6b86301
ggml : tiny ggml_vec_dot_q4_K_q8_K AVX2 improvement (#2819)
|
2 years ago |
 Kawrakow
|
bac66994cf
Quantization imrovements for k_quants (#2707)
|
2 years ago |
 Lee
|
a9559bf77b
ggml : workaround for missing _mm256_setr_m128i in GCC < 8 in k_quants.c (#2405)
|
2 years ago |
 katsu560
|
be2301bcda
k_quants : add AVX support to dot functions with QK_K as 64 (#2339)
|
2 years ago |
|
Kawrakow
|
42f70cb2f6
Fix scalar version of Q5_K when QK_K = 64 (#2362)
|
2 years ago |
 Georgi Gerganov
|
9225baef71
k-quants : fix indentation
|
2 years ago |
|
katsu560
|
5743ca8092
k-quants : add AVX support to dot functions (#1916)
|
2 years ago |
|
Kawrakow
|
6769e944c7
k-quants : support for super-block size of 64 (#2001)
|
2 years ago |
 Artyom Lebedev
|
3f1223155a
k-quants : GCC12 compilation fix (#1792)
|
2 years ago |
|
Georgi Gerganov
|
0bf7cf1b29
Revert "ggml : load data into int8x16x4_t using vld4q_s8 on arm64 (#1738)"
|
2 years ago |
 le.chang
|
8432d4d9f7
ggml : load data into int8x16x4_t using vld4q_s8 on arm64 (#1738)
|
2 years ago |
|
Georgi Gerganov
|
5c64a0952e
k-quants : allow to optionally disable at compile time (#1734)
|
2 years ago |
