ExternalVendorCode/whisper.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/whisper.cpp.git synced 2024-12-19 20:57:52 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

ggml-cpu: fix typo in gemv/gemm iq4_nl_4_4 (llama/10580)

Browse Source
This commit is contained in:
Shupei Fan 2024-11-29 21:49:02 +08:00 committed by Georgi Gerganov
parent 964b154a2a
commit cb847c20a7
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
ggml/src/ggml-cpu/ggml-cpu-aarch64.c
View File

@ -1020,7 +1020,7 @@ void ggml_gemv_iq4_nl_4x4_q8_0(int n, float * restrict s, size_t bs, const void
float * res_ptr = s;
for (int x = 0; x < nc / ncols_interleaved; x++) {
const block_q4_0x4 * b_ptr = (const block_q4_0x4 *) vx + (x * nb);
const block_iq4_nlx4 * b_ptr = (const block_iq4_nlx4 *) vx + (x * nb);
float32x4_t sumf = vdupq_n_f32(0);
for (int l = 0; l < nb; l++) {
@ -3507,7 +3507,7 @@ void ggml_gemm_iq4_nl_4x4_q8_0(int n, float * restrict s, size_t bs, const void
for (int y = 0; y < nr / 4; y++) {
const block_q8_0x4 * a_ptr = (const block_q8_0x4 *) vy + (y * nb);
for (int x = 0; x < nc / ncols_interleaved; x++) {
const block_q4_0x4 * b_ptr = (const block_q4_0x4 *) vx + (x * nb);
const block_iq4_nlx4 * b_ptr = (const block_iq4_nlx4 *) vx + (x * nb);
float32x4_t sumf[4];
for (int m = 0; m < 4; m++) {