Mirrors/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-24 13:28:50 +01:00
Code Issues Packages Projects Releases Wiki Activity

ggml : fix unnecessary f32 -> f16 -> f32 casts (mmla) (#5951)

Browse Source
This commit is contained in:
Georgi Gerganov 2024-03-09 17:36:20 +02:00 committed by GitHub
parent 58308a0ecc
commit 8380ecfb21
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 4 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
ggml-quants.c
View File

@ -4059,10 +4059,10 @@ void ggml_vec_dot_q4_1_q8_1(int n, float * restrict s, size_t bs, const void * r
const int8x16_t y1_h = vld1q_s8(b_y1->qs + 16);
// mmla into int32x4_t
float32x4_t scale = {GGML_FP16_TO_FP32(b_x0->d)*GGML_FP16_TO_FP32(b_y0->d),
GGML_FP16_TO_FP32(b_x0->d)*GGML_FP16_TO_FP32(b_y1->d),
GGML_FP16_TO_FP32(b_x1->d)*GGML_FP16_TO_FP32(b_y0->d),
GGML_FP16_TO_FP32(b_x1->d)*GGML_FP16_TO_FP32(b_y1->d)};
float32x4_t scale = {GGML_FP16_TO_FP32(b_x0->d)*b_y0->d,
GGML_FP16_TO_FP32(b_x0->d)*b_y1->d,
GGML_FP16_TO_FP32(b_x1->d)*b_y0->d,
GGML_FP16_TO_FP32(b_x1->d)*b_y1->d};
int8x16_t l0 = vreinterpretq_s8_s64(vzip1q_s64(vreinterpretq_s64_s8(x0_l), vreinterpretq_s64_s8(x1_l)));
int8x16_t l1 = vreinterpretq_s8_s64(vzip2q_s64(vreinterpretq_s64_s8(x0_l), vreinterpretq_s64_s8(x1_l)));