haraldwolff/llama.cpp
1
0
Fork 0
Code Issues Pull requests Packages Projects Releases Wiki Activity

ggml : try fix 32-bit arm compat (whisper/1938)

Browse source 
* ggml : try fix 32-bit arm compat

* ggml : fix cont
This commit is contained in:
Georgi Gerganov 2024-03-08 23:45:07 +02:00
parent bf47a5eefc
commit df4dc3e7cb
No known key found for this signature in database
GPG key ID: 449E073F9DC10735
1 changed files with 8 additions and 7 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

15
ggml-quants.c
View file

@ -9009,8 +9009,8 @@ void ggml_vec_dot_iq2_s_q8_K(int n, float * restrict s, size_t bs, const void *
static const uint8_t k_mask2[16] = {0x01, 0x02, 0x04, 0x08, 0x10, 0x20, 0x40, 0x80, 0x01, 0x02, 0x04, 0x08, 0x10, 0x20, 0x40, 0x80,};
const uint8x16x2_t mask1 = vld1q_u8_x2(k_mask1);
const uint8x16_t mask2 = vld1q_u8(k_mask2);
const ggml_uint8x16x2_t mask1 = ggml_vld1q_u8_x2(k_mask1);
const uint8x16_t mask2 = vld1q_u8(k_mask2);
const uint8x16_t m1 = vdupq_n_u8(1);
const int32x4_t vzero = vdupq_n_s32(0);
@ -9354,11 +9354,12 @@ void ggml_vec_dot_iq3_s_q8_K (int n, float * restrict s, size_t bs, const void *
static const int16_t k_shift[8] = {8, 7, 6, 5, 4, 3, 2, 1};
const uint8x16x2_t mask1 = vld1q_u8_x2(k_mask1);
const uint8x16_t mask2 = vld1q_u8(k_mask2);
const int16x8_t hshift = vld1q_s16(k_shift);
const uint16x8_t m256 = vdupq_n_u16(256);
const uint8x16_t m1 = vdupq_n_u8(1);
const ggml_uint8x16x2_t mask1 = ggml_vld1q_u8_x2(k_mask1);
const uint8x16_t mask2 = vld1q_u8(k_mask2);
const int16x8_t hshift = vld1q_s16(k_shift);
const uint16x8_t m256 = vdupq_n_u16(256);
const uint8x16_t m1 = vdupq_n_u8(1);
uint8x16x2_t vs;
ggml_int8x16x4_t q3s;