llama.cpp
SOLVE_TRI extension to more dimensions
#17793
Merged
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Overview
Commits
13
Changes
View On
GitHub
SOLVE_TRI extension to more dimensions
#17793
pwilkin
merged 13 commits into
ggml-org:master
from
pwilkin:tri_extend_cuda
pwilkin
requested a review
from
am17an
165 days ago
pwilkin
requested a review
from
JohannesGaessler
165 days ago
pwilkin
requested a review
from
ggerganov
165 days ago
github-actions
added
testing
github-actions
added
Nvidia GPU
github-actions
added
ggml
pwilkin
force pushed
from
468bec5a
to
5efca207
162 days ago
github-actions
added
examples
github-actions
added
server
am17an
commented on 2025-12-08
JohannesGaessler
commented on 2025-12-08
Extended TRI
a4d38e40
Fix whitespace
11e4ca64
chore: update webui build output
2a1bde9c
Just use cuBLAS for everything...
b5e41a78
Merge both versions
60dcf1be
pwilkin
force pushed
from
c8abbe00
to
60dcf1be
161 days ago
pwilkin
requested a review
from
JohannesGaessler
160 days ago
pwilkin
requested a review
from
am17an
160 days ago
Merge branch 'master' into tri_extend_cuda
9aa3a925
Remove incorrect imports causing failures for CI
b14aec01
Still failing... remove all direct cublas imports and rely on common …
5d861911
Defines for hipBlas
978a79d6
Aaaand MUSA defines...
c3bcdd22
I hate this job...
eda6ab7b
Stupid typo...
026bea32
JohannesGaessler
approved these changes on 2025-12-11
Update ggml/src/ggml-cuda/solve_tri.cu
08a003e1
pwilkin
merged
53ecd4fd
into master
158 days ago
Login to write a write a comment.
Login via GitHub
Reviewers
JohannesGaessler
am17an
ggerganov
Assignees
No one assigned
Labels
testing
Nvidia GPU
examples
server
ggml
Milestone
No milestone
Login to write a write a comment.
Login via GitHub