]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 0843245)
ggml-cpu: Conditionally enable power11 backend based on compiler support (#24687)
authorshalinib-ibm <redacted>
Wed, 17 Jun 2026 18:45:19 +0000 (00:15 +0530)
committerGitHub <redacted>
Wed, 17 Jun 2026 18:45:19 +0000 (02:45 +0800)
commit2e88c49c90f0add8796f633fea8c3d65b975f295
treea68e9fdc3ed27c25b8c04ef535b5a1622ef18851tree
parent0843245cb1ed0129c81c0ae58c633329c496a3d7commit | diff
ggml-cpu: Conditionally enable power11 backend based on compiler support (#24687)

* ggml: Conditionally enable power11 backend based on compiler support

Guard POWER11 backend creation behind a compiler flag check for -mcpu=power11. This avoids build failures on current GCC/Clang toolchains while preserving forward compatibility once POWER11 support becomes available.

* Update CMakeLists.txt

ggml-cpu: Use -mcpu=power10 for P10 and P11
ggml/src/CMakeLists.txt diff | blob | history
ggml/src/ggml-cpu/CMakeLists.txt diff | blob | history
Packaging of ggml-org/llama.cpp