]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 8a3519b)
vulkan: iGPU memory reporting fix (#17110)
authorRuben Ortlam <redacted>
Sun, 9 Nov 2025 08:54:47 +0000 (09:54 +0100)
committerGitHub <redacted>
Sun, 9 Nov 2025 08:54:47 +0000 (09:54 +0100)
commit7f3e9d339c99d96d6df9833c63ec27dbbc96f003
tree49cea72f8d9e55cc0e30c1a1db4e18fb48990529tree
parent8a3519b70898b07ec05c391418a05aaa6b377c83commit | diff
vulkan: iGPU memory reporting fix (#17110)

* vulkan: use all device-local heaps for memory availability reporting

Co-authored-by: Giuseppe Scrivano <redacted>
* use all available heaps for iGPU memory reporting

* Allow multiple memory types per buffer request for devices with split heaps

---------

Co-authored-by: Giuseppe Scrivano <redacted>
ggml/src/ggml-vulkan/ggml-vulkan.cpp diff | blob | history
Packaging of ggml-org/llama.cpp