Lumpiasty/llama.cpp
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

CUDA: batch out_prod inner loop with cublasSgemmStridedBatched (#22651)

Browse Source 
* CUDA: batch out_prod inner loop with cublasSgemmStridedBatched

* CUDA: batch out_prod inner loop with cublasSgemmStridedBatched

* CUDA: add cublasSgemmStridedBatched mapping for HIP and MUSA backends
This commit is contained in:
leonardHONG
2026-05-07 21:59:29 +02:00
committed by GitHub
parent aaf4a4d5e0
commit 05ff59cb57
4 changed files with 31 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-cuda/vendors/hip.h
Vendored
+1
View File
@@ -48,6 +48,7 @@
#define cublasSetMathMode(handle, mode) CUBLAS_STATUS_SUCCESS
#define cublasSetStream hipblasSetStream
#define cublasSgemm hipblasSgemm
#define cublasSgemmStridedBatched hipblasSgemmStridedBatched
#define cublasStatus_t hipblasStatus_t
#define cublasOperation_t hipblasOperation_t
#define cudaDevAttrCooperativeLaunch hipDeviceAttributeCooperativeLaunch