mirror of
https://github.com/ggerganov/whisper.cpp.git
synced 2025-05-01 22:54:53 +02:00
ggml-cuda: Adding support for unified memory (llama/8035)
* Adding support for unified memory * adding again the documentation about unified memory * refactoring: Moved the unified memory code in the correct location. * Fixed compilation error when using hipblas * cleaning up the documentation * Updating the documentation Co-authored-by: Johannes Gäßler <johannesg@5d6.de> * adding one more case where the PR should not be enabled --------- Co-authored-by: matteo serva <matteo.serva@gmail.com> Co-authored-by: Johannes Gäßler <johannesg@5d6.de>
This commit is contained in:
parent
d26250f78c
commit
8e39ee171f
@ -130,7 +130,22 @@ static cudaError_t ggml_cuda_device_malloc(void ** ptr, size_t size, int device)
|
||||
}
|
||||
return res;
|
||||
#else
|
||||
|
||||
#if !defined(GGML_USE_HIPBLAS) && !defined(GGML_USE_MUSA)
|
||||
cudaError_t err;
|
||||
if (getenv("GGML_CUDA_ENABLE_UNIFIED_MEMORY") != nullptr)
|
||||
{
|
||||
err = cudaMallocManaged(ptr, size);
|
||||
}
|
||||
else
|
||||
{
|
||||
err = cudaMalloc(ptr, size);
|
||||
}
|
||||
return err;
|
||||
#else
|
||||
return cudaMalloc(ptr, size);
|
||||
#endif // !defined(GGML_USE_HIPBLAS) && !defined(GGML_USE_MUSA)
|
||||
|
||||
#endif
|
||||
}
|
||||
|
||||
|
Loading…
Reference in New Issue
Block a user