jdelony/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-06-27 23:50:20 -05:00
Code Issues Packages Projects Releases Wiki Activity

ggml-cpu: use runtime SVE width in FWHT (#24059)

Browse Source
This commit is contained in:
Charles Xu 2026-06-03 12:45:10 +02:00 committed by GitHub
parent f8f0a47a55
commit 3571fa5435
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 10 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
ggml/src/ggml-cpu/ops.cpp
View File

@ -8955,7 +8955,12 @@ static void ggml_compute_forward_flash_attn_ext_f16(
k->type == v->type &&
neq1 >= Q_TILE_SZ);
#ifdef GGML_SIMD
use_tiled &= (DV % GGML_F32_EPR == 0);
#if defined(__ARM_FEATURE_SVE)
const int64_t f32_epr = svcntw();
#else
const int64_t f32_epr = GGML_F32_EPR;
#endif
use_tiled &= (DV % f32_epr == 0);
#endif
int current_chunk = ith;
@ -11358,7 +11363,11 @@ static void ggml_compute_forward_fwht_f32(const ggml_compute_params * params, gg
// Scalar passes
#if defined(GGML_SIMD)
#if defined(__ARM_FEATURE_SVE)
const int step = svcntw();
#else
const int step = GGML_F32_EPR;
#endif
#else
const int step = n;
#endif