]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 924518e)
ggml : do not define GGML_USE_CUDA when building with GGML_BACKEND_DL (#11211)
authorRadoslav Gerganov <redacted>
Mon, 13 Jan 2025 11:31:41 +0000 (13:31 +0200)
committerGitHub <redacted>
Mon, 13 Jan 2025 11:31:41 +0000 (13:31 +0200)
commit1244cdcf14900dd199907b13f25d9c91a507f578
tree3a8c6a963f494f9c7424bcb28a2f15c19b95d8c6tree
parent924518e2e5726e81f3aeb2518fb85963a500e93acommit | diff
ggml : do not define GGML_USE_CUDA when building with GGML_BACKEND_DL (#11211)

Build fails when using HIP and GGML_BACKEND_DL:
```
/usr/bin/ld: ../ggml/src/libggml.so: undefined reference to `ggml_backend_cuda_reg'
collect2: error: ld returned 1 exit status
```
This patch fixes this.
ggml/src/ggml-hip/CMakeLists.txt diff | blob | history
Packaging of ggml-org/llama.cpp