diff options
| author | Djip007 <djip.perois@free.fr> | 2024-05-28 01:40:47 +0200 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2024-05-28 01:40:47 +0200 |
| commit | 852aafb163d32d5bad63c10bc323a02c28fec59d (patch) | |
| tree | 48c9bf7791952889c83da7ee3085818d7a61fa25 /ggml-cuda | |
| parent | 0136966dafb452601c23f30395878d5a65ddc559 (diff) | |
update HIP_UMA #7399 (#7414)
* update HIP_UMA #7399
add use of hipMemAdviseSetCoarseGrain when LLAMA_HIP_UMA is enable.
- get x2 on prompte eval and x1.5 on token gen with rocm6.0 on ryzen 7940HX iGPU (780M/gfx1103)
* simplify code, more consistent style
---------
Co-authored-by: slaren <slarengh@gmail.com>
Diffstat (limited to 'ggml-cuda')
| -rw-r--r-- | ggml-cuda/common.cuh | 5 |
1 files changed, 0 insertions, 5 deletions
diff --git a/ggml-cuda/common.cuh b/ggml-cuda/common.cuh index 8f6fd71c..22872ca5 100644 --- a/ggml-cuda/common.cuh +++ b/ggml-cuda/common.cuh @@ -79,13 +79,8 @@ #define cudaHostRegisterReadOnly hipHostRegisterReadOnly #define cudaHostUnregister hipHostUnregister #define cudaLaunchHostFunc hipLaunchHostFunc -#ifdef GGML_HIP_UMA -#define cudaMalloc hipMallocManaged -#define cudaMallocHost(ptr, size) hipHostMalloc(ptr, size) -#else #define cudaMalloc hipMalloc #define cudaMallocHost(ptr, size) hipHostMalloc(ptr, size, hipHostMallocDefault) -#endif #define cudaMemcpy hipMemcpy #define cudaMemcpyAsync hipMemcpyAsync #define cudaMemcpyPeerAsync hipMemcpyPeerAsync |