]> git.djapps.eu Git - pkg/ggml/sources/whisper.cpp/commit
ggml : do not define GGML_USE_CUDA when building with GGML_BACKEND_DL (llama/11211)
authorRadoslav Gerganov <redacted>
Mon, 13 Jan 2025 11:31:41 +0000 (13:31 +0200)
committerGeorgi Gerganov <redacted>
Tue, 14 Jan 2025 08:38:01 +0000 (10:38 +0200)
commita4b00bcaaf88e188db539521246c9d88d238d0fb
tree836a09d99bf407c7b008a70b2e4bfc2514d3e022
parentcdb8aa2f2e9d6486497758984503e1d72d88fd14
ggml : do not define GGML_USE_CUDA when building with GGML_BACKEND_DL (llama/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