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

Browse Source

* 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

...

This commit is contained in:

Srihari-mcw 2025-03-20 17:05:34 +05:30 committed by Georgi Gerganov

parent ae6a9bb9a5

commit 8058f19d0b

1 changed files with 1493 additions and 12 deletions

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1505

ggml/src/ggml-cpu/ggml-cpu-aarch64.cpp

File diff suppressed because it is too large Load Diff