Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

ggml : try fix 32-bit arm compat #1938

Merged
merged 2 commits into from Mar 8, 2024
Merged

ggml : try fix 32-bit arm compat #1938

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
2abc2d7
ggml : try fix 32-bit arm compat
ggerganov Mar 8, 2024
faba651
ggml : fix cont
ggerganov Mar 8, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Jump to
Jump to file
Failed to load files.
Diff view
Diff view
15 changes: 8 additions & 7 deletions ggml-quants.c
View file
Open in desktop
Expand Up @@ -9758,8 +9758,8 @@ 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);

Expand Down Expand Up @@ -10103,11 +10103,12 @@ void ggml_vec_dot_iq3_s_q8_K (int n, float * GGML_RESTRICT s, size_t bs, const v

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;
Expand Down