root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2025-01-14 04:24:30 +00:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

Fix after merge with latest master

Browse Source
This commit is contained in:
Iwan Kawrakow 2024-02-12 07:38:29 +02:00
parent dc0b14bebb
commit 67e7c4238e
2 changed files with 3 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
ggml-quants.c
View File

@ -9307,6 +9307,7 @@ void ggml_vec_dot_iq1_s_q8_K (int n, float * GGML_RESTRICT s, size_t bs, const
const __m128i m8 = _mm_set1_epi8(0x08);
const __m128i m7 = _mm_set1_epi8(0x07);
const __m128i m1 = _mm_set1_epi8(0x01);
const __m128i shuffle_h = _mm_set_epi8(15, 7, 14, 6, 13, 5, 12, 4, 11, 3, 10, 2, 9, 1, 8, 0);
const __m128i shuffle_s[4] = {
_mm_set_epi32(0x03030303, 0x02020202, 0x01010101, 0x00000000),
@ -9334,7 +9335,7 @@ void ggml_vec_dot_iq1_s_q8_K (int n, float * GGML_RESTRICT s, size_t bs, const
const __m128i qh = _mm_shuffle_epi8(_mm_set_epi64x(aux64 >> 4, aux64), shuffle_h);
const __m256i hbit = _mm256_cvtepi8_epi16(_mm_and_si128(qh, m8));
v_gindex = _mm256_or_si256(_mm256_cvtepi8_epi16(ql), _mm256_slli_epi16(hbit, 5));
const __m128i scales = _mm_and_si128(qh, m7);
const __m128i scales = _mm_or_si128(_mm_slli_epi16(_mm_and_si128(qh, m7), 1), m1);
for (int i32 = 0; i32 < 4; ++i32) {
const __m256i q8b = _mm256_loadu_si256((const __m256i*)q8); q8 += 32;

1
ggml.c
View File

@ -683,6 +683,7 @@ static const ggml_type_traits_t type_traits[GGML_TYPE_COUNT] = {
.from_float_reference = NULL,
.vec_dot = ggml_vec_dot_iq1_s_q8_K,
.vec_dot_type = GGML_TYPE_Q8_K,
.nrows = 1,
},
[GGML_TYPE_Q8_K] = {
.type_name = "q8_K",