llama.cpp
CUDA: refactor mmq, dmmv, mmvq
#7716
Merged

CUDA: refactor mmq, dmmv, mmvq #7716

JohannesGaessler
JohannesGaessler CUDA: refactor mmq, dmmv, mmvq
158e3d3e
JohannesGaessler
slaren
slaren commented on 2024-06-03
github-actions github-actions added build
github-actions github-actions added Nvidia GPU
github-actions github-actions added python
github-actions github-actions added ggml
JohannesGaessler fix out-of-bounds write
bd8422db
JohannesGaessler struct for qk, qr, qi
8b6962dd
JohannesGaessler JohannesGaessler force pushed from 79d415d5 to 8b6962dd 1 year ago
JohannesGaessler
JohannesGaessler fix cmake build
fe1c4bbf
github-actions
slaren
slaren approved these changes on 2024-06-04
mofosyne mofosyne added refactoring
mofosyne mofosyne added Review Complexity : High
JohannesGaessler mmq_type_traits
fd65ff31
JohannesGaessler JohannesGaessler merged 7d1a378b into master 1 year ago

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
Milestone