From 12b063f0ecf280e98028e444fc492ee6222cdcdc Mon Sep 17 00:00:00 2001
From: Kyle Liang <liangmanlai@gmail.com>
Date: Sun, 11 Jun 2023 21:20:52 +0800
Subject: [PATCH] Fixed WSL cuda's OOM error (#1594)

* In the function , add the cuda error bypass.

* remove excessive codes and prints

---------

Co-authored-by: liang <liangmanlai@126.com>
---
 ggml-cuda.cu | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/ggml-cuda.cu b/ggml-cuda.cu
index a62f26e1e..4f2195f77 100644
--- a/ggml-cuda.cu
+++ b/ggml-cuda.cu
@@ -1105,6 +1105,9 @@ void * ggml_cuda_host_malloc(size_t size) {
     void * ptr = nullptr;
     cudaError_t err = cudaMallocHost((void **) &ptr, size);
     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",
             size/1024.0/1024.0, cudaGetErrorString(err));
         return nullptr;