llama.cpp
Fix ffn_down quantization mix for MoE models
#4927
Merged

Fix ffn_down quantization mix for MoE models #4927

ikawrakow merged 3 commits into master from ik/fix_qxm_moe
ikawrakow
Fix ffn_down quantization mix for MoE models
998b635a
Fix the fix
121eb066
ggerganov
ggerganov approved these changes on 2024-01-14
Review suggestion
00cc67e2
ikawrakow ikawrakow merged a128c38d into master 1 year ago
ikawrakow ikawrakow deleted the ik/fix_qxm_moe branch 1 year ago

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
Milestone