cturan/llama.cpp

ggml : block interleaving support for Q4_K quantization for x86 AVX2 architecture (#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

Srihari-mcw 10 months ago

parent

732b5fbf5e

commit

3d82dbcbce

1 changed files with 1349 additions and 0 deletions

Split View Show Diff Stats

				
					File diff suppressed because it is too large
					
						+ 1349
						
						- 0
					
ggml/src/ggml-cpu/ggml-cpu-aarch64.cpp

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

File diff suppressed because it is too large + 1349 - 0 ggml/src/ggml-cpu/ggml-cpu-aarch64.cpp

Some files were not shown because too many files changed in this diff

File diff suppressed because it is too large
+ 1349 - 0
ggml/src/ggml-cpu/ggml-cpu-aarch64.cpp