llama.cpp
CUDA: fixed redundant value dequantization
#4809
Merged

CUDA: fixed redundant value dequantization #4809

JohannesGaessler
slaren
slaren approved these changes on 2024-01-07
slaren
ggerganov
ggerganov commented on 2024-01-07
JohannesGaessler CUDA: fixed redundant value dequantization
42b54f14
JohannesGaessler JohannesGaessler force pushed to 42b54f14 2 years ago
JohannesGaessler
ggerganov
ggerganov approved these changes on 2024-01-07
JohannesGaessler
ggerganov
ggerganov approved these changes on 2024-01-07
JohannesGaessler JohannesGaessler merged d5a410e8 into master 2 years ago

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
Milestone