]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 3f08ef2)
CUDA: Support CUDA Virtual Devices (#25228)
authorAnav Prasad <redacted>
Thu, 16 Jul 2026 10:37:35 +0000 (03:37 -0700)
committerGitHub <redacted>
Thu, 16 Jul 2026 10:37:35 +0000 (13:37 +0300)
commit79bba02a6741de194912d370015866414faa83ad
tree717186733caf4d38902de22c581d34ad33c48dabtree
parent3f08ef2c519710831cb68c8dc2c2693e6bb5bf81commit | diff
CUDA: Support CUDA Virtual Devices (#25228)

* support cuda virtual devices

* disable NCCL path when virtual devices are used

* label virtual devices in description; add GPUx2 server CI jobs

* code refactor
.github/workflows/server-self-hosted.yml diff | blob | history
ggml/src/ggml-cuda/common.cuh diff | blob | history
ggml/src/ggml-cuda/ggml-cuda.cu diff | blob | history
Packaging of ggml-org/llama.cpp