CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-17 11:37:10 +00:00
Code Issues Packages Projects Releases Wiki Activity

CANN: add support for ACL Graph (#15065)

Browse Source 
* feat(cann): add optional support for ACL Graph execution

This commit adds support for executing ggml computational graphs using
Huawei's ACL graph mode via the USE_CANN_GRAPH flag. The support can be
enabled at compile time using the CMake option:

    -DUSE_CANN_GRAPH=ON

By default, ACL graph execution is **disabled**, and the fallback path
uses node-by-node execution.

Key additions:
- CMake option  to toggle graph mode
- Graph capture and execution logic using
- Tensor property matching to determine whether graph update is required
- Safe fallback and logging if the environment variable LLAMA_SET_ROWS
  is unset or invalid

This prepares the backend for performance improvements in repetitive graph
execution scenarios on Ascend devices.

Signed-off-by: noemotiovon <757486878@qq.com>

* Fix review comments

Signed-off-by: noemotiovon <757486878@qq.com>

* remane USE_CANN_GRAPH to USE_ACL_GRAPH

Signed-off-by: noemotiovon <757486878@qq.com>

* fix typo

Signed-off-by: noemotiovon <757486878@qq.com>

---------

Signed-off-by: noemotiovon <757486878@qq.com>
This commit is contained in:
Chenguang Li
2025-08-06 14:12:42 +08:00
committed by GitHub
parent 9515c6131a
commit 2241453252
3 changed files with 231 additions and 22 deletions
Download Patch File Download Diff File Expand all files Collapse all files

36
ggml/src/ggml-cann/common.h
View File

@@ -337,6 +337,29 @@ private:
int32_t device_;
};
#ifdef USE_ACL_GRAPH
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];
int32_t op_params[GGML_MAX_OP_PARAMS / sizeof(int32_t)];
};
struct ggml_cann_graph {
~ggml_cann_graph() {
if (graph != nullptr) {
aclmdlRIDestroy(graph);
}
}
aclmdlRI graph = nullptr;
std::vector<ggml_graph_node_properties> ggml_graph_properties;
};
#endif // USE_ACL_GRAPH
/**
* @brief Context for managing CANN backend operations.
*/
@@ -345,8 +368,13 @@ struct ggml_backend_cann_context {
std::string name; /**< Name of the device. */
std::string description; /**< Description of the device. */
aclrtEvent copy_event = nullptr; /**< Event for managing copy operations. */
#ifdef USE_ACL_GRAPH
/// Cached CANN ACL graph used for executing the current ggml computation graph.
std::unique_ptr<ggml_cann_graph> cann_graph;
#endif
cann_task_queue task_queue;
bool async_mode;
bool support_set_rows;
aclrtStream streams[GGML_CANN_MAX_STREAMS] = {nullptr}; /**< Array of streams for the device. */
@@ -362,6 +390,14 @@ struct ggml_backend_cann_context {
async_mode = parse_bool(get_env("GGML_CANN_ASYNC_MODE").value_or(""));
GGML_LOG_INFO("%s: device %d async operator submission is %s\n", __func__,
device, async_mode ? "ON" : "OFF");
support_set_rows = parse_bool(get_env("LLAMA_SET_ROWS").value_or(""));
GGML_LOG_INFO("%s: LLAMA_SET_ROWS is %s\n", __func__, support_set_rows ? "ON" : "OFF");
if (!support_set_rows) {
GGML_LOG_INFO("%s: CANN Graph currently only supports execution when LLAMA_SET_ROWS is ON. "
"Falling back to eager mode.\n", __func__);
}
}
/**