llama.cpp
cuda : enable CUDA graphs for MMID 1 <= BS <= 4
#19645
Merged
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Overview
Commits
3
Changes
View On
GitHub
cuda : enable CUDA graphs for MMID 1 <= BS <= 4
#19645
ggerganov
merged 3 commits into
master
from
gg/cuda-graphs-enable-bs-gt1
github-actions
added
Nvidia GPU
github-actions
added
ggml
ggerganov
requested a review
from
JohannesGaessler
4 days ago
ggerganov
requested a review
from
am17an
4 days ago
am17an
commented on 2026-02-15
Base automatically changed from
gg/graph-fix-kq-mask-reuse
to
master
3 days ago
ggerganov
requested a review
from
CISC
3 days ago
cuda : enable CUDA graphs for MMID BS <= 4
7d0be2c4
ggerganov
force pushed
from
15a68420
to
7d0be2c4
3 days ago
ORippler
commented on 2026-02-16
ggerganov
commented on 2026-02-16
cont : add stream capture check
dd9af011
JohannesGaessler
approved these changes on 2026-02-17
cont : add MMVQ_MMID_MAX_BATCH_SIZE
573b94ca
ggerganov
merged
ad8207af
into master
2 days ago
ggerganov
deleted the gg/cuda-graphs-enable-bs-gt1 branch
2 days ago
Login to write a write a comment.
Login via GitHub
Reviewers
JohannesGaessler
am17an
ORippler
CISC
Assignees
No one assigned
Labels
Nvidia GPU
ggml
Milestone
No milestone
Login to write a write a comment.
Login via GitHub