llama.cpp
ggml-cuda: fix blackwell native builds
#18361
Merged

ggml-cuda: fix blackwell native builds #18361

am17an
github-actions github-actions added Nvidia GPU
github-actions github-actions added ggml
am17an am17an force pushed from cb5828da to b869eb8d 55 days ago
am17an am17an force pushed from e138e27f to 6f04e410 55 days ago
JohannesGaessler
JohannesGaessler commented on 2025-12-25
am17an
am17an
JohannesGaessler
JohannesGaessler commented on 2025-12-25
ggml-cuda: fix blackwell native builds
818ba588
replace for GGML_NATIVE=OFF too
907b8405
only replace for native
b9a692e9
am17an am17an force pushed from 0f30f404 to 55ea0a7e 55 days ago
am17an am17an force pushed from 55ea0a7e to b9a692e9 55 days ago
JohannesGaessler
JohannesGaessler approved these changes on 2025-12-25
CISC
am17an
CISC
am17an
CISC
am17an remove 120f-virtual for default compilation
bd3acd00
CISC
am17an
am17an
CISC
CISC
am17an am17an merged b0fb0f0a into master 55 days ago
am17an am17an deleted the cuda-fix-blackwell-native-build branch 55 days ago
JohannesGaessler
CISC
am17an
CISC
Panchovix
am17an
Panchovix
am17an
am17an
KiruyaMomochi
am17an
timkhronos
LeXaMeN
JohannesGaessler

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
Milestone