tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-08-27 02:28:19 -04:00
Code Issues Packages Projects Releases Wiki Activity

Documented CUDA reproducibility, added warning (#1346)

Browse Source
This commit is contained in:
Johannes Gäßler
2023-05-08 02:42:01 +02:00
committed by GitHub
parent e1295513a4
commit 1f48b0abcf
3 changed files with 6 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
ggml-cuda.cu
View File

@@ -348,7 +348,7 @@ static void ggml_cuda_pool_free(void * ptr, size_t size) {
CUDA_CHECK(cudaFree(ptr));
}
#define GGML_CUDA_MAX_STREAMS 8
#define GGML_CUDA_MAX_STREAMS 8 // Set this to 1 for reproducible matrix multiplication.
#define GGML_CUDA_MAX_EVENTS 64
static cublasHandle_t g_cublasH = nullptr;
static cudaStream_t g_cudaStreams[GGML_CUDA_MAX_STREAMS] = { nullptr };