Skip to content

Commit d70a53a

Browse files
Srihari-mcwIvy233
authored andcommitted
ggml : block interleaving support for Q4_K quantization for x86 AVX2 architecture (ggml-org#12332)
* Add block interleaving support for Q4_K quantization * Remove whitespaces and fix CI/CD issues * Update pointer of bsums from int16_t to const int16_t * Add vector version of quantize_q8_K_4x8 function * Update code formatting based on review comments
1 parent 06d5f99 commit d70a53a

File tree

1 file changed

+1493
-12
lines changed

1 file changed

+1493
-12
lines changed

0 commit comments

Comments
 (0)