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

SOLVE_TRI extension to more dimensions (#17793)

Browse Source 
* Extended TRI

* Fix whitespace

* chore: update webui build output

* Just use cuBLAS for everything...

* Merge both versions

* Remove incorrect imports causing failures for CI

* Still failing... remove all direct cublas imports and rely on common imports from "common.cuh"

* Defines for hipBlas

* Aaaand MUSA defines...

* I hate this job...

* Stupid typo...

* Update ggml/src/ggml-cuda/solve_tri.cu

Co-authored-by: Johannes Gäßler <johannesg@5d6.de>

---------

Co-authored-by: Johannes Gäßler <johannesg@5d6.de>
This commit is contained in:
Piotr Wilkin (ilintar)
2025-12-11 17:20:43 +01:00
committed by GitHub
co-authored by Johannes Gäßler
parent c6f6e4f96a
commit 53ecd4fdb9
6 changed files with 125 additions and 20 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-cuda/vendors/hip.h
Vendored
+4
View File
@@ -19,6 +19,9 @@
#define CUDA_R_16F HIPBLAS_R_16F
#define CUDA_R_16BF HIPBLAS_R_16B
#define CUDA_R_32F HIPBLAS_R_32F
#define CUBLAS_SIDE_RIGHT HIPBLAS_SIDE_RIGHT
#define CUBLAS_FILL_MODE_UPPER HIPBLAS_FILL_MODE_UPPER
#define CUBLAS_DIAG_NON_UNIT HIPBLAS_DIAG_NON_UNIT
#define CU_DEVICE_ATTRIBUTE_VIRTUAL_MEMORY_MANAGEMENT_SUPPORTED hipDeviceAttributeVirtualMemoryManagementSupported
#define CU_MEM_ALLOC_GRANULARITY_RECOMMENDED hipMemAllocationGranularityRecommended
#define CU_MEM_ALLOCATION_TYPE_PINNED hipMemAllocationTypePinned
@@ -30,6 +33,7 @@
#define __shfl_xor_sync(mask, var, laneMask, width) __shfl_xor(var, laneMask, width)
#define __all_sync(mask, var) __all(var)
#define __any_sync(mask, var) __any(var)
#define cublasStrsmBatched hipblasStrsmBatched
#define cublasCreate hipblasCreate
#define cublasDestroy hipblasDestroy
#define cublasGemmEx hipblasGemmEx
ggml/src/ggml-cuda/vendors/musa.h
Vendored
+5
View File
@@ -12,11 +12,16 @@
#define CUBLAS_GEMM_DEFAULT_TENSOR_OP MUBLAS_GEMM_DEFAULT
#define CUBLAS_OP_N MUBLAS_OP_N
#define CUBLAS_OP_T MUBLAS_OP_T
#define CUBLAS_DEFAULT_MATH MUBLAS_DEFAULT_MATH
#define CUBLAS_SIDE_RIGHT MUBLAS_SIDE_RIGHT
#define CUBLAS_FILL_MODE_UPPER MUBLAS_FILL_MODE_UPPER
#define CUBLAS_DIAG_NON_UNIT MUBLAS_DIAG_NON_UNIT
#define CUBLAS_STATUS_SUCCESS MUBLAS_STATUS_SUCCESS
#define CUBLAS_TF32_TENSOR_OP_MATH MUBLAS_TENSOR_OP_MATH
#define CUDA_R_16F MUSA_R_16F
#define CUDA_R_16BF MUSA_R_16BF
#define CUDA_R_32F MUSA_R_32F
#define cublasStrsmBatched mublasStrsmBatched
#define cublasComputeType_t cudaDataType_t
#define cublasCreate mublasCreate
#define cublasDestroy mublasDestroy