CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-17 11:37:10 +00:00
Code Issues Packages Projects Releases Wiki Activity

ggml : fix conv2d_dw SVE path (ggml/1380)

Browse Source 
* Fix test-conv2d-dw failure on ARM SVE by using runtime vector length

The ggml_compute_forward_conv_2d_dw_cwhn function was using a hardcoded GGML_F32_EPR (8) for SIMD vectorization, but on ARM SVE the actual vector length varies by hardware. This caused incorrect computation when processing CWHN layout tensors on ARM machines.

Fix by using svcntw() to get the runtime SVE vector length instead of the compile-time constant.

Co-authored-by: ggerganov <1991296+ggerganov@users.noreply.github.com>

* ci : reduce sam score threshold

* ci : update bbox checks for sam test

---------

Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>
Co-authored-by: ggerganov <1991296+ggerganov@users.noreply.github.com>
This commit is contained in:
Georgi Gerganov
2025-11-04 20:40:52 +02:00
parent 9aa63374f2
commit 852ce5180a
1 changed files with 5 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
ggml/src/ggml-cpu/ops.cpp
View File

@@ -7084,7 +7084,11 @@ static void ggml_compute_forward_conv_2d_dw_cwhn(
const int64_t row_end = MIN(row_start + rows_per_thread, rows_total);
#ifdef GGML_SIMD
const int64_t pkg_size = GGML_F32_EPR;
#if defined(__ARM_FEATURE_SVE)
const int64_t pkg_size = svcntw();
#else
const int64_t pkg_size = GGML_F32_EPR;
#endif
const int64_t pkg_count = c / pkg_size;
const int64_t c_pkg_end = pkg_count * pkg_size;
#else