llama.cpp
Block interleaving support for Q4_K quantization for x86 AVX2 architecture
#12332
Merged
Overview
Commits
5
Changes
View On GitHub

Block interleaving support for Q4_K quantization for x86 AVX2 architecture #12332

ggerganov merged 5 commits into ggml-org:master from Srihari-mcw:q4k_block_interleaving
Srihari-mcw
Srihari-mcw Add block interleaving support for Q4_K quantization
fae86a56
github-actions github-actions added ggml
Srihari-mcw Remove whitespaces and fix CI/CD issues
33bab804
Srihari-mcw Update pointer of bsums from int16_t to const int16_t
022ad356
bartowski1182
Srihari-mcw
ggerganov
Srihari-mcw Add vector version of quantize_q8_K_4x8 function
cba0df39
Srihari-mcw
ggerganov
ggerganov approved these changes on 2025-03-19
Srihari-mcw Update code formatting based on review comments
adb86d7d
ggerganov ggerganov merged 3d82dbcb into master 272 days ago
Yangxiaoz
fairydreaming
ggerganov
Nor7th
Srihari-mcw
Nor7th
ggerganov
sultanqasim
bartowski1182
sultanqasim
sultanqasim
sultanqasim
sultanqasim
slaren
sultanqasim
longaaalong
Srihari-mcw

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
ggml
Milestone
No milestone
Terms Of Use Privacy Policy Refund Policy Impressum