Introduction of CUDA Graphs to LLama.cpp (#6766)

* DRAFT: Introduction of CUDA Graphs to LLama.cpp

* FIx issues raised in comments

* Tidied to now only use CUDA runtime (not mixed with driver calls)

* disable for multi-gpu and batch size > 1

* Disable CUDA graphs for old GPU arch and with env var

* added missing CUDA_CHECKs

* Addressed comments

* further addressed comments

* limit to GGML_ALLOW_CUDA_GRAPHS defined in llama.cpp cmake

* Added more comprehensive graph node checking

* With mechanism to fall back if graph capture fails

* Revert "With mechanism to fall back if graph capture fails"

This reverts commit eb9f15fb6f.

* Fall back if graph capture fails and address other comments

* - renamed GGML_ALLOW_CUDA_GRAPHS to GGML_CUDA_USE_GRAPHS

- rename env variable to disable CUDA graphs to GGML_CUDA_DISABLE_GRAPHS

- updated Makefile build to enable CUDA graphs

- removed graph capture failure checking in ggml_cuda_error
  using a global variable to track this is not thread safe, but I am also not safistied with checking an error by string
  if this is necessary to workaround some issues with graph capture with eg. cuBLAS, we can pass the ggml_backend_cuda_context to the error checking macro and store the result in the context

- fixed several resource leaks

- fixed issue with zero node graphs

- changed fixed size arrays to vectors

- removed the count of number of evaluations before start capturing, and instead changed the capture mode to relaxed

- removed the check for multiple devices so that it is still possible to use a single device, instead checks for split buffers to disable cuda graphs with -sm row

- changed the op for checking batch size to GGML_OP_ADD, should be more reliable than GGML_OP_SOFT_MAX

- code style fixes

- things to look into
  - VRAM usage of the cudaGraphExec_t, if it is significant we may need to make it optional
  - possibility of using cudaStreamBeginCaptureToGraph to keep track of which ggml graph nodes correspond to which cuda graph nodes

* fix build without cuda graphs

* remove outdated comment

* replace minimum cc value with a constant

---------

Co-authored-by: slaren <slarengh@gmail.com>

ggml-cuda/common.cuh

@@ -19,6 +19,7 @@
 #include <cassert>
 #include <cfloat>
 #include <string>
+#include <vector>
 
 #if defined(GGML_USE_HIPBLAS)
 #include <hip/hip_runtime.h>
@@ -526,6 +527,43 @@ struct ggml_tensor_extra_gpu {
     cudaEvent_t events[GGML_CUDA_MAX_DEVICES][GGML_CUDA_MAX_STREAMS]; // events for synchronizing multiple GPUs
 };
 
+
+#if (CUDART_VERSION >= 12000) && defined(GGML_CUDA_USE_GRAPHS)
+#define USE_CUDA_GRAPH
+#endif
+
+struct ggml_graph_node_properties {
+    void * node_address;
+    ggml_op node_op;
+    int64_t ne[GGML_MAX_DIMS];
+    size_t nb[GGML_MAX_DIMS];
+    void * src_address[GGML_MAX_SRC];
+};
+
+struct ggml_cuda_graph {
+#ifdef USE_CUDA_GRAPH
+    ~ggml_cuda_graph() {
+        if (instance != nullptr) {
+            CUDA_CHECK(cudaGraphExecDestroy(instance));
+        }
+        if (graph != nullptr) {
+            CUDA_CHECK(cudaGraphDestroy(graph));
+        }
+    }
+    cudaGraph_t graph = nullptr;
+    cudaGraphExec_t instance = nullptr;
+    size_t num_nodes = 0;
+    std::vector<cudaGraphNode_t> nodes;
+    std::vector<cudaKernelNodeParams> params;
+    bool disable_due_to_gpu_arch = false;
+    bool disable_due_to_too_many_updates = false;
+    bool disable_due_to_failed_graph_capture = false;
+    int number_consecutive_updates = 0;
+    std::vector<ggml_graph_node_properties> ggml_graph_properties;
+    std::vector<char **> updated_kernel_arg;
+#endif
+};
+
 struct ggml_backend_cuda_context {
     int device;
     std::string name;
@@ -534,6 +572,8 @@ struct ggml_backend_cuda_context {
     cudaStream_t streams[GGML_CUDA_MAX_DEVICES][GGML_CUDA_MAX_STREAMS] = { { nullptr } };
     cublasHandle_t cublas_handles[GGML_CUDA_MAX_DEVICES] = {nullptr};
 
+    std::unique_ptr<ggml_cuda_graph> cuda_graph;
+
     explicit ggml_backend_cuda_context(int device) :
         device(device),
         name(GGML_CUDA_NAME + std::to_string(device)) {