vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Merge branch 'master' into concedo_experimental

Browse source 
# Conflicts:
#	.github/workflows/build.yml
#	README.md
This commit is contained in:
Concedo 2023-05-08 11:12:42 +08:00
commit 1083876a1b
2 changed files with 4 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

3
examples/common.cpp
View file

@ -100,6 +100,9 @@ bool gpt_params_parse(int argc, char ** argv, gpt_params & params) {
arg = argv[i];
if (arg == "-s" || arg == "--seed") {
#if defined(GGML_USE_CUBLAS)
fprintf(stderr, "WARNING: when using cuBLAS generation results are NOT guaranteed to be reproducible.\n");
#endif
if (++i >= argc) {
invalid_param = true;
break;

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 };