]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 78d2f52)
ggml: Update VMM Pool allocation ggml-cuda.cu - Turing P2P access fix (fixes #24489...
authorVexxie <redacted>
Sun, 5 Jul 2026 17:10:09 +0000 (18:10 +0100)
committerGitHub <redacted>
Sun, 5 Jul 2026 17:10:09 +0000 (19:10 +0200)
commit7a63fdede1aca8b29e64146f33ae03af6c3ee3cd
tree90b88b0efc26424976814ac4da92e92233a7cc9atree
parent78d2f524682d9fee790a6460c93d018dafeb5229commit | diff
ggml: Update VMM Pool allocation ggml-cuda.cu - Turing P2P access fix (fixes #24489) (#24491)

* Update ggml-cuda.cu - Turing P2P access fix.

* Add original code as fallback behaviour when NCCL or P2P is not set/true.

* Update ggml/src/ggml-cuda/ggml-cuda.cu to add comment as per suggestion

Co-authored-by: Johannes Gäßler <redacted>
---------

Co-authored-by: Johannes Gäßler <redacted>
ggml/src/ggml-cuda/ggml-cuda.cu diff | blob | history
Packaging of ggml-org/llama.cpp