Hugging Face's logo

Spaces:
natasa365
/
whisper.cpp
Sleeping

App Files Community
Srihari-mcw commited on
Commit
0729506
·
1 Parent(s): 3a7ca19

ggml : block interleaving support for Q4_K quantization for x86 AVX2 architecture (llama/12332)

Browse files

* 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

Files changed (1) hide show
  1. ggml/src/ggml-cpu/ggml-cpu-aarch64.cpp +0 -0
ggml/src/ggml-cpu/ggml-cpu-aarch64.cpp CHANGED
The diff for this file is too large to render. See raw diff