176e9097cf
This change addresses the PowerPC build breakage noted in the review discussion of #13427. Specifically: - Include ggml-cpu PowerPC backend sources in the rsync filter so they are propagated from llama/vendor into Ollama’s vendored ggml snapshot. - Apply upstream ggml fixes required for PowerPC builds, including the vector macro collision fix and conditional POWER11 backend enablement. Without syncing the PowerPC backend sources, ggml-cpu is incomplete in Ollama and PPC builds remain broken even with the upstream fixes applied. Signed-off-by: Shalini Salomi Bodapati <Shalini.Salomi.Bodapati@ibm.com> |
||
|---|---|---|
| .. | ||
| ggml | ||
| ggml.go | ||
| ggml_test.go | ||
| quantization.go | ||
| threads.go | ||
| threads_debug.go | ||