CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-08 10:07:01 +00:00
Code Issues Packages Projects Releases Wiki Activity

Hip: disable VMM on hip as it seams that it dosent work in some configurations (#11420)

Browse Source
This commit is contained in:
uvos
2025-01-25 21:01:12 +01:00
committed by GitHub
parent ca6baf76c1
commit 26771a1491
4 changed files with 14 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
ggml/src/ggml-cuda/common.cuh
View File

@@ -131,6 +131,10 @@ typedef float dfloat; // dequantize float
typedef float2 dfloat2;
#endif // GGML_CUDA_F16
#if (!defined(GGML_USE_HIP) && !defined(GGML_CUDA_NO_VMM)) || (defined(GGML_USE_HIP) && !defined(GGML_HIP_NO_VMM))
#define GGML_USE_VMM
#endif // (!defined(GGML_USE_HIP) && !defined(GGML_CUDA_NO_VMM)) || (defined(GGML_USE_HIP) && !defined(GGML_HIP_NO_VMM))
#if (defined(GGML_USE_HIP) && defined(__HIP_PLATFORM_AMD__)) || __CUDA_ARCH__ >= GGML_CUDA_CC_PASCAL
#define FP16_AVAILABLE
#endif // (defined(GGML_USE_HIP) && defined(__HIP_PLATFORM_AMD__)) || __CUDA_ARCH__ >= GGML_CUDA_CC_PASCAL