From: Kyle Liang <redacted>
Date: Sun, 11 Jun 2023 13:20:52 +0000 (+0800)
Subject: Fixed WSL cuda's OOM error (#1594)
X-Git-Tag: gguf-v0.4.0~646
X-Git-Url: https://git.djapps.eu/?a=commitdiff_plain;h=12b063f0ecf280e98028e444fc492ee6222cdcdc;p=pkg%2Fggml%2Fsources%2Fllama.cpp

Fixed WSL cuda's OOM error (#1594)

* In the function , add the cuda error bypass.

* remove excessive codes and prints

---------

Co-authored-by: liang <redacted>
---

diff --git a/ggml-cuda.cu b/ggml-cuda.cu
index a62f26e1..4f2195f7 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;