vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

ggml : introduce structs for the q4 data blocks (#356)

Browse source 
* Introduce structs for the q4 data blocks

* ggml : rename quant struct variables + fix ARM_NEON

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
Stephan Walter 2023-03-28 15:56:03 +00:00 • committed by GitHub
parent e0670260fb
commit c1f885067c
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
6 changed files with 150 additions and 235 deletions
Download patch file Download diff file Expand all files Collapse all files

4
tests/test-quantize.c
View file

@ -13,7 +13,7 @@ int main(void) {
src[i] = (float)(i + 1);
}
size_t size = ggml_quantize_q4_0(src, dst, QK, QK, QK, hist);
size_t size = ggml_quantize_q4_0(src, dst, QK, QK, hist);
assert(size == 20);
float max_result = ((float *)dst)[0];
float max_expected = src[31] / ((1 << 3) - 1);
@ -24,7 +24,7 @@ int main(void) {
assert(q4_result == q4_expected);
}
size = ggml_quantize_q4_1(src, dst, QK, QK, QK, hist);
size = ggml_quantize_q4_1(src, dst, QK, QK, hist);
assert(size == 24);
float delta_result = ((float *)dst)[0];
float delta_expected = (src[31] - src[0]) / ((1 << 4) - 1);