ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-02-27 00:24:11 +00:00
Code Issues Packages Projects Releases Wiki Activity

Minor

Browse Source
This commit is contained in:
Iwan Kawrakow
2025-04-13 08:34:43 +03:00
parent 29773692f1
commit 4291d7e1e6
1 changed files with 1 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
ggml/src/ggml-quants.c
View File

@@ -14643,9 +14643,7 @@ static void quantize_row_iq1_m_impl(const float * restrict x, void * restrict vy
}
}
if (sumq2_f > 0) d = sumqx_f/sumq2_f;
//s.f16 = GGML_FP32_TO_FP16(d*1.1125f); // 1.1125f is another fudge factor. Don't ask me why it is needed.
//s.f16 = GGML_FP32_TO_FP16(d*1.0625f); // 1.1125f is another fudge factor. Don't ask me why it is needed.
s.f16 = GGML_FP32_TO_FP16(d*1.085f); // 1.1125f is another fudge factor. Don't ask me why it is needed.
s.f16 = GGML_FP32_TO_FP16(d*1.085f); // 1.085f is another fudge factor. Don't ask me why it is needed.
sc[0] |= ((s.u16 & 0x000f) << 12);
sc[1] |= ((s.u16 & 0x00f0) << 8);
sc[2] |= ((s.u16 & 0x0f00) << 4);