nikola/llama_cpp
1
0
Fork 0
Code Issues Pull Requests Actions 34 Packages Projects Releases Wiki Activity

ggml : LoongArch fixes (#16958)

Browse Source 
* Fix test-quantize-fns f16 and q4_0 failed when use LSX

* Fix LoongArch set float intrinsic when use LSX/LASX
This commit is contained in:
Jinyang He
2025-11-03 08:40:02 +02:00
committed by GitHub
parent ee3a5a10ad
commit fcfce040e8
3 changed files with 32 additions and 31 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-cpu/arch/loongarch/quants.c
+4 -5
View File
@@ -700,7 +700,8 @@ void ggml_vec_dot_q4_0_q8_0(int n, float * GGML_RESTRICT s, size_t bs, const voi
for (; ib + 1 < nb; ib += 2) {
// Compute combined scale for the block 0 and 1
const __m128 d_0_1 = (__m128)__lsx_vreplgr2vr_w( GGML_CPU_FP16_TO_FP32(x[ib].d) * GGML_CPU_FP16_TO_FP32(y[ib].d) );
const float ft0 = GGML_CPU_FP16_TO_FP32(x[ib].d) * GGML_CPU_FP16_TO_FP32(y[ib].d);
const __m128 d_0_1 = (__m128)(v4f32){ft0, ft0, ft0, ft0};
const __m128i tmp_0_1 = __lsx_vld((const __m128i *)x[ib].qs, 0);
@@ -714,11 +715,9 @@ void ggml_vec_dot_q4_0_q8_0(int n, float * GGML_RESTRICT s, size_t bs, const voi
bx_1 = __lsx_vsub_b(bx_1, off);
const __m128i i32_1 = mul_sum_i8_pairs(bx_1, by_1);
//_mm_prefetch(&x[ib] + 2 * sizeof(block_q4_0), _MM_HINT_T0);
//_mm_prefetch(&y[ib] + 2 * sizeof(block_q8_0), _MM_HINT_T0);
// Compute combined scale for the block 2 and 3
const __m128 d_2_3 = (__m128)__lsx_vreplgr2vr_w( GGML_CPU_FP16_TO_FP32(x[ib + 1].d) * GGML_CPU_FP16_TO_FP32(y[ib + 1].d) );
const float ft1 = GGML_CPU_FP16_TO_FP32(x[ib + 1].d) * GGML_CPU_FP16_TO_FP32(y[ib + 1].d);
const __m128 d_2_3 = (__m128)(v4f32){ft1, ft1, ft1, ft1};
const __m128i tmp_2_3 = __lsx_vld((const __m128i *)x[ib + 1].qs, 0);