llama: update vendored code to commit 40c6d79f (#7875)

llama/patches/0001-cuda.patch

@@ -4,47 +4,33 @@ Date: Thu, 6 Jun 2024 23:55:47 -0700
 Subject: [PATCH] cuda
 
 ---
- ggml/include/ggml-cuda.h | 2 ++
- ggml/src/ggml-backend.c  | 5 +++++
- ggml/src/ggml-cuda.cu    | 6 ++++--
- 3 files changed, 11 insertions(+), 2 deletions(-)
+ ggml/src/ggml-backend.cpp       | 5 +++++
+ ggml/src/ggml-cuda/ggml-cuda.cu | 4 ++++
+ 2 files changed, 9 insertions(+)
 
-diff --git a/ggml/include/ggml-cuda.h b/ggml/include/ggml-cuda.h
-index 71bb6dcf..08be0895 100644
---- a/ggml/include/ggml-cuda.h
-+++ b/ggml/include/ggml-cuda.h
-@@ -34,6 +34,8 @@ GGML_API GGML_CALL ggml_backend_buffer_type_t ggml_backend_cuda_split_buffer_typ
- // pinned host buffer for use with the CPU backend for faster copies between CPU and GPU
- GGML_API GGML_CALL ggml_backend_buffer_type_t ggml_backend_cuda_host_buffer_type(void);
- 
-+GGML_API GGML_CALL int ggml_backend_cuda_reg_devices();
-+
- GGML_API GGML_CALL int  ggml_backend_cuda_get_device_count(void);
- GGML_API GGML_CALL void ggml_backend_cuda_get_device_description(int device, char * description, size_t description_size);
- GGML_API GGML_CALL void ggml_backend_cuda_get_device_memory(int device, size_t * free, size_t * total);
-diff --git a/ggml/src/ggml-backend.c b/ggml/src/ggml-backend.c
-index ba280e06..d5c3fe49 100644
---- a/ggml/src/ggml-backend.c
-+++ b/ggml/src/ggml-backend.c
-@@ -83,7 +83,12 @@ void ggml_backend_buffer_free(ggml_backend_buffer_t buffer) {
+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 hipblas backends because
++// 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_HIPBLAS)
-     free(buffer);
++#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.cu b/ggml/src/ggml-cuda.cu
-index 6efdab14..809d6ab1 100644
---- a/ggml/src/ggml-cuda.cu
-+++ b/ggml/src/ggml-cuda.cu
-@@ -469,6 +469,10 @@ GGML_CALL static bool ggml_backend_buffer_is_cuda(ggml_backend_buffer_t buffer)
- GGML_CALL static void ggml_backend_cuda_buffer_free_buffer(ggml_backend_buffer_t buffer) {
+diff --git a/ggml/src/ggml-cuda/ggml-cuda.cu b/ggml/src/ggml-cuda/ggml-cuda.cu
+index d6e4bfdd..52aec229 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;
 +
@@ -53,13 +39,4 @@ index 6efdab14..809d6ab1 100644
 +    free(buffer);
  }
  
- GGML_CALL static void * ggml_backend_cuda_buffer_get_base(ggml_backend_buffer_t buffer) {
-@@ -3204,8 +3208,6 @@ GGML_CALL static ggml_backend_t ggml_backend_reg_cuda_init(const char * params,
-     GGML_UNUSED(params);
- }
- 
--extern "C" GGML_CALL int ggml_backend_cuda_reg_devices();
--
- GGML_CALL int ggml_backend_cuda_reg_devices() {
-     int device_count = ggml_backend_cuda_get_device_count();
-     //int device_count = 1; // DEBUG: some tools require delaying CUDA initialization
+ static bool ggml_backend_buffer_is_cuda(ggml_backend_buffer_t buffer) {