]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 69c28f1)
CUDA: check for buffer overlap before fusing (#21566)
authorAman Gupta <redacted>
Tue, 7 Apr 2026 16:57:04 +0000 (00:57 +0800)
committerGitHub <redacted>
Tue, 7 Apr 2026 16:57:04 +0000 (00:57 +0800)
commitde1aa6fa73e135839109e09fec1a0997f4207b2a
tree436c6bfb2d1890ae6a726dc5f7383a8610e88250tree
parent69c28f1547c169902f62ca48bee75fb876c4d8e6commit | diff
CUDA: check for buffer overlap before fusing (#21566)

* CUDA: check for buffer overlap before fusing

* use ggml_cuda_check_fusion_memory_ranges
ggml/src/ggml-cuda/ggml-cuda.cu diff | blob | history
Packaging of ggml-org/llama.cpp