llama.cpp
Use full range for q4_0 quantization
#729
Merged
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Overview
Commits
6
Changes
View On
GitHub
Use full range for q4_0 quantization
#729
ggerganov
merged 6 commits into
ggml-org:master
from
unbounded:q4_0_range_fix
ggerganov
added
high priority
ggerganov
added
research 🔬
ggerganov
assigned
unbounded
3 years ago
Use full range for q4_0 quantization
f57433c4
Update quantize_row_q4_0 for AVX/AVX2
84aa7d83
Update quantize_row_q4_0 for WASM
73a92d2d
Update quantize_row_q4_0 for Arm NEON
fea8d101
Update quantize_row_q4_0 for PowerPC
d09f97e2
unbounded
force pushed
to
5808fcf7
3 years ago
Use full range for q4_2 quantization
5808fcf7
ggerganov
approved these changes on 2023-04-25
ggerganov
merged
dd0eabc0
into master
3 years ago
Login to write a write a comment.
Login via GitHub
Reviewers
ggerganov
Assignees
unbounded
Labels
high priority
research 🔬
Milestone
No milestone
Login to write a write a comment.
Login via GitHub