CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-18 11:46:58 +00:00
Code Issues Packages Projects Releases Wiki Activity

CUDA/HIP: add support for selectable warp size to mmv (#11519)

Browse Source 
CUDA/HIP: add support for selectable warp size to mmv
This commit is contained in:
uvos
2025-02-02 22:40:09 +01:00
committed by GitHub
parent 4d0598e144
commit 396856b400
3 changed files with 34 additions and 14 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
ggml/src/ggml-cuda/vendors/hip.h vendored
View File

@@ -1,5 +1,6 @@
#pragma once
#define HIP_ENABLE_WARP_SYNC_BUILTINS 1
#include <hip/hip_runtime.h>
#include <hipblas/hipblas.h>
#include <hip/hip_fp16.h>
@@ -8,6 +9,7 @@
// for rocblas_initialize()
#include "rocblas/rocblas.h"
#endif // __HIP_PLATFORM_AMD__
#define CUBLAS_COMPUTE_16F HIPBLAS_R_16F
#define CUBLAS_COMPUTE_32F HIPBLAS_R_32F
#define CUBLAS_COMPUTE_32F_FAST_16F HIPBLAS_R_32F