ollama/llama/patches/0001-cuda.patch

From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
From: jmorganca <jmorganca@gmail.com>
Date: Thu, 6 Jun 2024 23:55:47 -0700
Subject: [PATCH] cuda

---
 ggml/src/ggml-backend.cpp       | 5 +++++
 ggml/src/ggml-cuda/ggml-cuda.cu | 4 ++++
 2 files changed, 9 insertions(+)

diff --git a/ggml/src/ggml-backend.cpp b/ggml/src/ggml-backend.cpp
index fdb4b986..9b80fe07 100644
--- a/ggml/src/ggml-backend.cpp
+++ b/ggml/src/ggml-backend.cpp
@@ -106,7 +106,12 @@ void ggml_backend_buffer_free(ggml_backend_buffer_t buffer) {
     if (buffer->iface.free_buffer != NULL) {
         buffer->iface.free_buffer(buffer);
     }
+
+// TODO: this needs to be freed in cuda and hip backends because
+// the cuda backend implementation compiled with msvc
+#if !defined(GGML_USE_CUDA) && !defined(GGML_USE_HIP)
     delete buffer;
+#endif
 }
 
 size_t ggml_backend_buffer_get_size(ggml_backend_buffer_t buffer) {
diff --git a/ggml/src/ggml-cuda/ggml-cuda.cu b/ggml/src/ggml-cuda/ggml-cuda.cu
index c180adc8..000f1777 100644
--- a/ggml/src/ggml-cuda/ggml-cuda.cu
+++ b/ggml/src/ggml-cuda/ggml-cuda.cu
@@ -424,6 +424,10 @@ struct ggml_backend_cuda_buffer_context {
 static void ggml_backend_cuda_buffer_free_buffer(ggml_backend_buffer_t buffer) {
     ggml_backend_cuda_buffer_context * ctx = (ggml_backend_cuda_buffer_context *)buffer->context;
     delete ctx;
+
+    // TODO: this needs to be freed in cuda and hipblas backends because
+    // the cuda backend implementation compiled with msvc
+    free(buffer);
 }
 
 static bool ggml_backend_buffer_is_cuda(ggml_backend_buffer_t buffer) {