]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 0754b7b)
fix: CUDA device PCI bus ID de-dupe OOMing (ignoring other 3 gpus entirely) (#22533)
authorlucy <redacted>
Sat, 2 May 2026 20:19:25 +0000 (16:19 -0400)
committerGitHub <redacted>
Sat, 2 May 2026 20:19:25 +0000 (22:19 +0200)
commitd05fe1d7dadbf8943c8f1903fcf65b935ddab839
tree2974d64b268aa659276888738bc91b0734f2acd7tree
parent0754b7b6fe6109909786bdaa763111167b7410c8commit | diff
fix: CUDA device PCI bus ID de-dupe OOMing (ignoring other 3 gpus entirely) (#22533)

* fix: CUDA device PCI bus ID detection for multi-GPU de-dupe

* HIP, MUSA macros

---------

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