llama.cpp
CUDA: optimize Orin single-column MMVQ
#31268
Merged

CUDA: optimize Orin single-column MMVQ #31268

meitmt
meitmt CUDA: optimize Orin single-column MMVQ
ad985565
meitmt meitmt requested a review 23 days ago
github-actions github-actions added ggml
github-actions github-actions added CUDA
Andy1314Chen
meitmt
JohannesGaessler
JohannesGaessler commented on 2026-11-10
meitmt Create a separate Orin branch in `calc_rows_per_block`
408835df
JohannesGaessler
JohannesGaessler approved these changes on 2026-11-11
JohannesGaessler JohannesGaessler added merge ready
ggerganov ggerganov merged ea84d709 into master 4 hours ago

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
Milestone