Mirrors/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-26 14:20:31 +01:00
Code Issues Packages Projects Releases Wiki Activity

Fixed WSL cuda's OOM error (#1594)

Browse Source 
* In the function , add the cuda error bypass.

* remove excessive codes and prints

---------

Co-authored-by: liang <liangmanlai@126.com>
This commit is contained in:
Kyle Liang 2023-06-11 21:20:52 +08:00 committed by GitHub
parent 31d2b5f4a4
commit 12b063f0ec
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 3 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
ggml-cuda.cu
View File

@ -1105,6 +1105,9 @@ void * ggml_cuda_host_malloc(size_t size) {
void * ptr = nullptr; void * ptr = nullptr;
cudaError_t err = cudaMallocHost((void **) &ptr, size); cudaError_t err = cudaMallocHost((void **) &ptr, size);
if (err != cudaSuccess) { if (err != cudaSuccess) {
// The allocation error can be bypassed. A null ptr will assigned out of this function.
// This can fixed the OOM error in WSL.
cudaGetLastError();
fprintf(stderr, "WARNING: failed to allocate %.2f MB of pinned memory: %s\n", fprintf(stderr, "WARNING: failed to allocate %.2f MB of pinned memory: %s\n",
size/1024.0/1024.0, cudaGetErrorString(err)); size/1024.0/1024.0, cudaGetErrorString(err));
return nullptr; return nullptr;