llama.cpp
Use Q4_K for attn_v for Q2_K_S when n_gqa >= 4
#4996
Merged
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Overview
Commits
1
Changes
View On
GitHub
Use Q4_K for attn_v for Q2_K_S when n_gqa >= 4
#4996
ggerganov
merged 1 commit into
master
from
ik/better_q2_k_s
Use Q4_K for attn_v for Q2_K_S when n_gqa >= 4
9fd1e83f
ggerganov
approved these changes on 2024-01-17
ggerganov
merged
2b3a665d
into master
1 year ago
Login to write a write a comment.
Login via GitHub
Reviewers
ggerganov
Assignees
No one assigned
Labels
None yet
Milestone
No milestone
Login to write a write a comment.
Login via GitHub