]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 35fb824)
cuda : Enable CUDA Graph usage for Nemotron Nano v2 (NemotronH) (#16328)
authoranavp-nvidia <redacted>
Tue, 30 Sep 2025 08:13:22 +0000 (08:13 +0000)
committerGitHub <redacted>
Tue, 30 Sep 2025 08:13:22 +0000 (11:13 +0300)
commita014310374a16f9204f2bcc1b458fc1eda67e469
tree0171c92b9ce896ec6d6059b3d293c3e15d420cectree
parent35fb82497ec6c5904b0adb7e1c881a76c1c692dbcommit | diff
cuda : Enable CUDA Graph usage for Nemotron Nano v2 (NemotronH) (#16328)

* Fix Nemotron Nano v2 9B not executing as CUDA Graph on NVIDIA GPUs

* fix to ensure test-backend-ops check passes
ggml/src/ggml-cuda/cpy.cu diff | blob | history
ggml/src/ggml-cuda/ggml-cuda.cu diff | blob | history
src/llama-model.cpp diff | blob | history
Packaging of ggml-org/llama.cpp