Mirrors/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2025-01-14 06:19:02 +01:00
Code Issues Packages Projects Releases Wiki Activity

iq1_s: turn off SIMD implementation for QK_K = 64 (it does not work)

Browse Source
This commit is contained in:
Iwan Kawrakow 2024-02-28 08:28:10 +02:00
parent 47d52b2b24
commit f0cbb6ddf6
1 changed files with 4 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
ggml-quants.c
View File

@ -10291,7 +10291,8 @@ void ggml_vec_dot_iq1_s_q8_K (int n, float * GGML_RESTRICT s, size_t bs, const
const int nb = n / QK_K; const int nb = n / QK_K;
#if defined __ARM_NEON && QK_K != 64 // TODO: implement for QK_K = 64
#if defined __ARM_NEON && QK_K == 256
const uint8x16_t m8 = vdupq_n_u8(0x08); const uint8x16_t m8 = vdupq_n_u8(0x08);
const uint8x16_t m7 = vdupq_n_u8(0x07); const uint8x16_t m7 = vdupq_n_u8(0x07);
@ -10348,7 +10349,8 @@ void ggml_vec_dot_iq1_s_q8_K (int n, float * GGML_RESTRICT s, size_t bs, const
*s = sumf; *s = sumf;
#elif defined __AVX2__ // TODO: implement for QK_K = 64
#elif defined __AVX2__ && QK_K == 256
const __m128i m8 = _mm_set1_epi8(0x08); const __m128i m8 = _mm_set1_epi8(0x08);
const __m128i m7 = _mm_set1_epi8(0x07); const __m128i m7 = _mm_set1_epi8(0x07);